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

    Neuronpedia

    INDEX
    Explanations

    Nullable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _UC
    -0.07
    Train
    -0.07
    ᕼ
    -0.07
     dividing
    -0.07
     conducts
    -0.07
    _const
    -0.07
     bidi
    -0.07
    前十
    -0.07
    累计
    -0.07
    祲
    -0.07
    POSITIVE LOGITS
    Ą
    0.06
     ern
    0.06
    ------↵↵
    0.06
     tele
    0.06
    .V
    0.06
     regiment
    0.06
    rts
    0.06
     שאנחנו
    0.06
    [Y
    0.06
     dat
    0.06
    Act Density 0.001%

    No Known Activations