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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weather
    -0.07
    ilder
    -0.07
    valuator
    -0.06
     السم
    -0.06
    /object
    -0.06
     jud
    -0.06
    .preferences
    -0.06
    ThanOr
    -0.06
    oklyn
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     distractions
    0.08
    evento
    0.06
     invited
    0.06
     Spinner
    0.06
    413
    0.06
     подготов
    0.06
    roll
    0.06
     Mor
    0.06
    аниц
    0.06
     restaur
    0.06
    Act Density 0.068%

    No Known Activations