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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kaar
    -0.07
    .SuppressLint
    -0.06
     Ад
    -0.06
    .norm
    -0.06
     سان
    -0.06
     دارای
    -0.06
     Мор
    -0.06
     एज
    -0.06
     éxito
    -0.06
    .CREATED
    -0.06
    POSITIVE LOGITS
     Ankara
    0.07
     NOTIFY
    0.07
     山
    0.06
    _budget
    0.06
     lite
    0.06
    .'</
    0.06
    <th
    0.06
    attr
    0.06
    undi
    0.06
    ,p
    0.06
    Act Density 0.003%

    No Known Activations