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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ==↵
    -0.07
    >,
    -0.06
    Rh
    -0.06
     Alonso
    -0.06
    节
    -0.06
     summed
    -0.06
     seemed
    -0.06
     کوچ
    -0.06
     performers
    -0.06
    @",
    -0.06
    POSITIVE LOGITS
    (This
    0.08
     This
    0.07
    řím
    0.07
     예
    0.07
     فول
    0.07
     lubric
    0.07
     کردن
    0.07
    (initial
    0.07
    _WAIT
    0.07
     Ґ
    0.06
    Act Density 0.018%

    No Known Activations