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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绝佳
    -0.07
    为大家
    -0.07
     YYSTYPE
    -0.07
     onze
    -0.06
    .cloud
    -0.06
    Ҡ
    -0.06
    秦皇
    -0.06
    小编
    -0.06
    沨
    -0.06
    lke
    -0.06
    POSITIVE LOGITS
    Past
    0.07
     의미
    0.07
    /dis
    0.06
    OMET
    0.06
     prostitutas
    0.06
    .*?)
    0.06
     ah
    0.06
    MIN
    0.06
     farmer
    0.06
     bark
    0.06
    Act Density 0.125%

    No Known Activations