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

    Neuronpedia

    INDEX
    Explanations

    max count last

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens, especially floating-point constants with decimal fractions.

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

    technical references to programming components and licenses.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    crypto
    -0.07
    Sw
    -0.07
    DAQ
    -0.07
    Account
    -0.06
    orders
    -0.06
     Parser
    -0.06
    許
    -0.06
     differing
    -0.06
    chemistry
    -0.06
     Visa
    -0.06
    POSITIVE LOGITS
    awks
    0.06
    .AllowUser
    0.06
    ateg
    0.06
    ISION
    0.06
    イル
    0.06
    童
    0.06
     opatření
    0.06
    .HtmlControls
    0.06
     kappa
    0.06
     besar
    0.06
    Act Density 0.007%

    No Known Activations