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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (remote
    -0.07
     tho
    -0.07
     oo
    -0.07
    _private
    -0.07
     Только
    -0.06
     Monterey
    -0.06
     vn
    -0.06
    绝对是
    -0.06
    🛁
    -0.06
    농
    -0.06
    POSITIVE LOGITS
     generated
    0.07
    阳县
    0.07
     ;↵
    0.07
     McKin
    0.07
     Yö
    0.07
     Alive
    0.06
    𝙬
    0.06
     Eg
    0.06
    elden
    0.06
     Zah
    0.06
    Act Density 0.049%

    No Known Activations