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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PASSWORD
    -0.07
    ROWN
    -0.07
    Container
    -0.07
     permitted
    -0.07
     preserved
    -0.07
    우스
    -0.06
    ози
    -0.06
    azar
    -0.06
    cen
    -0.06
     mechanically
    -0.06
    POSITIVE LOGITS
     payoff
    0.08
    @qq
    0.07
    Off
    0.07
     كتاب
    0.07
    �
    0.07
    .DAO
    0.07
     Off
    0.06
    Guy
    0.06
    .ReadAll
    0.06
     IOCTL
    0.06
    Act Density 0.004%

    No Known Activations