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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    碰
    -0.07
    орту
    -0.06
     expenditure
    -0.06
    边
    -0.06
     دان
    -0.06
     ana
    -0.06
    нев
    -0.06
    _net
    -0.06
     Years
    -0.06
    鋼
    -0.06
    POSITIVE LOGITS
    gomery
    0.07
    EC
    0.07
     Bahamas
    0.06
    TA
    0.06
    /=
    0.06
    /form
    0.06
    sterdam
    0.06
    ask
    0.06
     آب
    0.06
     trump
    0.06
    Act Density 0.010%

    No Known Activations