Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    code examples related to obtaining column names from pandas dataframes in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron strongly responds to the special “<|start_header_id|>” token that marks the beginning of an assistant message header.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Account
    -0.07
     Voor
    -0.07
     수도
    -0.06
     browsers
    -0.06
    лара
    -0.06
     Addr
    -0.06
    kind
    -0.06
    anken
    -0.06
     cheapest
    -0.06
    DECREF
    -0.06
    POSITIVE LOGITS
     activities
    0.07
    震
    0.06
     unacceptable
    0.06
    \DependencyInjection
    0.06
    �
    0.06
     misrepresented
    0.06
     sout
    0.06
     conjug
    0.06
     scour
    0.06
     continuing
    0.06
    Act Density 0.109%

    No Known Activations