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

    Neuronpedia

    INDEX
    Explanations

    Times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    136
    -0.07
    >[
    -0.07
    führt
    -0.07
    Mount
    -0.06
    VAL
    -0.06
     buildings
    -0.06
    uation
    -0.06
     별
    -0.06
     Alley
    -0.06
     baik
    -0.06
    POSITIVE LOGITS
     PUB
    0.07
     Suc
    0.06
    stk
    0.06
     Май
    0.06
     бізнес
    0.06
    PJ
    0.06
    мп
    0.06
     rodz
    0.06
    制度
    0.06
     Nb
    0.06
    Act Density 0.120%

    No Known Activations