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

    Neuronpedia

    INDEX
    Explanations

    example.com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CONN
    -0.07
    睨
    -0.07
    touch
    -0.07
    遍
    -0.07
    .Names
    -0.07
    Cit
    -0.07
    眯
    -0.07
    pared
    -0.07
    טיבי
    -0.07
     commenc
    -0.07
    POSITIVE LOGITS
    зал
    0.08
    مستشار
    0.07
    พอใจ
    0.07
    ฉาก
    0.07
    �
    0.07
     bark
    0.06
    前世
    0.06
    谯
    0.06
    _LIMIT
    0.06
    سائل
    0.06
    Act Density 0.009%

    No Known Activations