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

    Neuronpedia

    INDEX
    Explanations

    Programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有多少
    -0.07
    Downloads
    -0.07
     sua
    -0.07
    ukan
    -0.07
     إليه
    -0.06
     moeten
    -0.06
    cdr
    -0.06
    radouro
    -0.06
    шие
    -0.06
    会计师
    -0.06
    POSITIVE LOGITS
     tarn
    0.07
    新世纪
    0.07
    Tumblr
    0.07
    科幻
    0.06
    蒎
    0.06
     κ
    0.06
    .effect
    0.06
    安检
    0.06
    生姜
    0.06
    _SCAN
    0.06
    Act Density 0.170%

    No Known Activations