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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.79
     بيها
    -0.55
    حياته
    -0.55
     Erl
    -0.53
     للمعارف
    -0.53
    thâu
    -0.53
    حياتها
    -0.52
    AddTagHelper
    -0.51
    LookAnd
    -0.51
     APPROACH
    -0.51
    POSITIVE LOGITS
     
    0.50
    |}{$
    0.49
    qrstuvwxyz
    0.48
    ZEN
    0.45
    contentLoaded
    0.43
     invokevirtual
    0.42
    tshell
    0.39
    OMI
    0.39
    AutoScaleMode
    0.39
    Ț
    0.39
    Act Density 0.021%

    No Known Activations