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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reasons
    -0.07
     무료
    -0.07
     okam
    -0.06
    .area
    -0.06
     Recru
    -0.06
     Goat
    -0.06
     αξ
    -0.06
     وب
    -0.06
    Poster
    -0.06
     полит
    -0.06
    POSITIVE LOGITS
    сім
    0.07
    ateur
    0.06
    amate
    0.06
    تهم
    0.06
    otlin
    0.06
    のような
    0.06
     lining
    0.06
    modified
    0.06
    (sf
    0.06
    <Key
    0.06
    Act Density 0.052%

    No Known Activations