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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обесп
    -0.07
    рой
    -0.07
     mascul
    -0.07
    چی
    -0.07
    andr
    -0.06
    付け
    -0.06
     established
    -0.06
    _unregister
    -0.06
     ؛
    -0.06
    torch
    -0.06
    POSITIVE LOGITS
    )\<
    0.07
    !!
    0.06
     ==(
    0.06
    onsense
    0.06
    ,,,,,,,,
    0.06
     DateTimeOffset
    0.06
    !
    0.06
    plx
    0.06
    πον
    0.06
     Paginator
    0.06
    Act Density 0.003%

    No Known Activations