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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spoiler
    -0.07
    Cách
    -0.07
    τικ
    -0.07
     Für
    -0.07
    _rows
    -0.06
     Hughes
    -0.06
     vampires
    -0.06
    Writing
    -0.06
    σσα
    -0.06
    重新
    -0.06
    POSITIVE LOGITS
     İt
    0.07
    athan
    0.07
     му
    0.07
     unbiased
    0.07
     aller
    0.06
     sala
    0.06
    ameron
    0.06
     roasted
    0.06
    서는
    0.06
     invitation
    0.06
    Act Density 0.000%

    No Known Activations