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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lively
    -0.07
    睫
    -0.07
    زن
    -0.07
    켬
    -0.06
    ˘
    -0.06
    ogne
    -0.06
    ⌕
    -0.06
    (trim
    -0.06
    쐴
    -0.06
     juicy
    -0.06
    POSITIVE LOGITS
    totals
    0.08
    chron
    0.07
    无敌
    0.07
     coût
    0.07
    .pagination
    0.07
     totalCount
    0.06
    냵
    0.06
     probabil
    0.06
    _commit
    0.06
    роз
    0.06
    Act Density 0.002%

    No Known Activations