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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    phrases related to public ownership and community engagement.

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

    This neuron detects form field labels—tokens like “First Name,” “Last Name,” “Email,” “Phone,” etc., used to prompt user input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Retrofit
    -0.07
    ат
    -0.07
    _tv
    -0.07
    .water
    -0.06
    İ
    -0.06
    .Bool
    -0.06
    itz
    -0.06
    ิท
    -0.06
    _FB
    -0.06
    'I
    -0.06
    POSITIVE LOGITS
     ise
    0.06
     SNP
    0.06
     Renderer
    0.06
    พน
    0.06
     unaware
    0.06
     chests
    0.06
     rẻ
    0.06
     overwrite
    0.06
     coorden
    0.06
    _versions
    0.06
    Act Density 0.006%

    No Known Activations