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

    Neuronpedia

    INDEX
    Explanations

    Math/algorithms papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INIT
    -0.06
    领
    -0.06
     SID
    -0.06
     CRS
    -0.06
     Lös
    -0.06
     pos
    -0.06
     irresist
    -0.06
     hl
    -0.06
    力气
    -0.06
     width
    -0.06
    POSITIVE LOGITS
     באר
    0.07
     segundos
    0.07
     Incorporated
    0.07
    '));
    0.07
    באר
    0.07
    يو
    0.07
    counts
    0.07
    vv
    0.07
    ⲟ
    0.07
    كتب
    0.07
    Act Density 0.018%

    No Known Activations