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

    Neuronpedia

    INDEX
    Explanations

    Citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    профессионал
    -0.08
    openssl
    -0.08
     ترك
    -0.07
    SURE
    -0.07
    国立
    -0.07
     Nghệ
    -0.07
     алкогол
    -0.07
     Sergey
    -0.07
    忘れ
    -0.07
    ND
    -0.07
    POSITIVE LOGITS
    _ASS
    0.07
    โบ
    0.07
     bulletin
    0.07
    .entry
    0.07
    (valid
    0.07
    (sql
    0.07
    霹
    0.07
    )(*
    0.07
    怎能
    0.07
    ˶
    0.07
    Act Density 0.016%

    No Known Activations