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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (especially floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Testament
    -0.07
    (APP
    -0.06
    .AnchorStyles
    -0.06
    ())
↵
↵
    -0.06
     obraz
    -0.06
     SN
    -0.06
    NU
    -0.06
    體
    -0.06
     Herc
    -0.06
     komp
    -0.06
    POSITIVE LOGITS
    _nama
    0.07
     versatility
    0.07
     fires
    0.06
    /var
    0.06
     З
    0.06
    _spaces
    0.06
     cardiovascular
    0.06
    (existing
    0.06
     všichni
    0.06
     automobiles
    0.06
    Act Density 0.015%

    No Known Activations