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

    Neuronpedia

    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on function‐ or method‐like expressions—i.e. identifiers immediately followed by “(…)”, whether in calls or declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code-related keywords and structures in programming languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ifes
    -0.07
    ball
    -0.07
     elf
    -0.07
     skin
    -0.07
    etter
    -0.07
    */}↵
    -0.06
     lors
    -0.06
     whales
    -0.06
    Hmm
    -0.06
    ор
    -0.06
    POSITIVE LOGITS
     )"
    0.07
    ItemSelectedListener
    0.07
     MIT
    0.06
     Recursive
    0.06
     firebase
    0.06
     Garmin
    0.06
    běh
    0.06
    -dismiss
    0.06
     Joseph
    0.06
     стоя
    0.06
    Act Density 0.019%

    No Known Activations