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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    technical details about how AI language models are created and trained.

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

    The neuron highlights words and phrases that express prerequisites or requirements (e.g. “need to have a basic understanding”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    986
    -0.07
     rockets
    -0.07
     Hard
    -0.06
     SCP
    -0.06
     Cons
    -0.06
     Roma
    -0.06
     COD
    -0.06
     org
    -0.06
    gy
    -0.06
     videog
    -0.06
    POSITIVE LOGITS
     чув
    0.07
    ają
    0.07
    -good
    0.06
    äs
    0.06
     je
    0.06
    amient
    0.06
    ies
    0.06
    -arrow
    0.06
     například
    0.06
    ías
    0.06
    Act Density 0.040%

    No Known Activations