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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disproportionate
    -0.07
     sof
    -0.07
    thumbnails
    -0.07
    gee
    -0.07
    ublik
    -0.07
     Kohana
    -0.07
    irk
    -0.06
    (lo
    -0.06
    yme
    -0.06
    whereIn
    -0.06
    POSITIVE LOGITS
    	div
    0.06
     pong
    0.06
    TAG
    0.06
     Tarif
    0.06
     traumat
    0.06
    हम
    0.06
    辺
    0.06
    -context
    0.06
    Initially
    0.06
    .ov
    0.06
    Act Density 0.017%

    No Known Activations