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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on explanatory comment text—especially the “returns …” phrases in function doc comments describing what a function returns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     indx
    -0.06
     cocos
    -0.06
     authority
    -0.06
     Temperature
    -0.06
     gamma
    -0.06
     packages
    -0.06
     Spiral
    -0.06
     Hour
    -0.06
    —that
    -0.06
     nó
    -0.06
    POSITIVE LOGITS
    .alignment
    0.07
    grow
    0.07
     getToken
    0.06
     *\
    0.06
    /layout
    0.06
    dff
    0.06
     decree
    0.06
    sendMessage
    0.06
    gunakan
    0.06
    .ConnectionStrings
    0.06
    Act Density 0.013%

    No Known Activations