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

    Neuronpedia

    INDEX
    Explanations

    biographical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _foreign
    -0.07
     编
    -0.07
    .GetLength
    -0.06
    нерг
    -0.06
    _strategy
    -0.06
    .controls
    -0.06
     zal
    -0.06
     ар
    -0.06
    ريل
    -0.06
    star
    -0.06
    POSITIVE LOGITS
    :.
    0.07
     rub
    0.06
     baths
    0.06
     Irish
    0.06
    _WS
    0.06
    .Features
    0.06
    enght
    0.06
     рік
    0.06
     zaz
    0.06
    uais
    0.06
    Act Density 0.003%

    No Known Activations