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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .decoder
    -0.07
    /show
    -0.06
    Vehicle
    -0.06
    ivatel
    -0.06
    disp
    -0.06
    械
    -0.06
    PACE
    -0.06
    .ax
    -0.06
     gez
    -0.06
    .marker
    -0.06
    POSITIVE LOGITS
     """
↵
↵
    0.07
    _ub
    0.07
     Honestly
    0.07
     отвер
    0.07
     بنا
    0.06
     tan
    0.06
     Sentence
    0.06
     uç
    0.06
    !")↵
    0.05
     удоб
    0.05
    Act Density 0.005%

    No Known Activations