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 never fires on any token—it appears to be inactive (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ("{\"
    -0.07
    IXEL
    -0.06
    PCODE
    -0.06
    寻
    -0.06
     kok
    -0.06
    ुम
    -0.06
    ニア
    -0.06
    ypsum
    -0.06
     ввод
    -0.06
     гри
    -0.05
    POSITIVE LOGITS
     ceremonial
    0.07
    ,line
    0.07
     battleground
    0.06
    recommend
    0.06
     sobě
    0.06
    ook
    0.06
     erk
    0.06
     să
    0.06
    .parameter
    0.06
    embedding
    0.06
    Act Density 0.044%

    No Known Activations