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

    Neuronpedia

    INDEX
    Explanations

    ot or III

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     празд
    -0.07
    โน
    -0.06
     ی
    -0.06
    ?family
    -0.06
     إذ
    -0.06
    :w
    -0.06
    .It
    -0.06
     vari
    -0.06
    guided
    -0.06
     factories
    -0.06
    POSITIVE LOGITS
    ographical
    0.07
    {
↵
↵
    0.07
    AMES
    0.07
     Runtime
    0.07
    Withdraw
    0.07
    ге
    0.06
     Scar
    0.06
     */}↵
    0.06
    _gradient
    0.06
    '],↵↵
    0.06
    Act Density 0.032%

    No Known Activations