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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Take
    -0.08
     toItem
    -0.07
    complexType
    -0.07
     Dez
    -0.07
     Reset
    -0.07
    _And
    -0.06
     confused
    -0.06
     adjustments
    -0.06
     Cent
    -0.06
     teg
    -0.06
    POSITIVE LOGITS
    眉
    0.08
    אורח
    0.07
    嫭
    0.07
     Lilly
    0.07
    Ѳ
    0.07
     showModal
    0.07
    .QRect
    0.06
     Larry
    0.06
    ❯
    0.06
    (sin
    0.06
    Act Density 0.007%

    No Known Activations