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

    Neuronpedia

    INDEX
    Explanations

    shift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KG
    -0.07
    Skill
    -0.07
    问道
    -0.06
     ys
    -0.06
    早早
    -0.06
    ENDOR
    -0.06
    nın
    -0.06
     FLOAT
    -0.06
    der
    -0.06
     Think
    -0.06
    POSITIVE LOGITS
     Rash
    0.07
    fecha
    0.07
    帮扶
    0.07
    _Trans
    0.07
    -----↵
    0.07
    linux
    0.07
    连
    0.07
    _THREADS
    0.07
    prec
    0.07
    ポート
    0.06
    Act Density 0.003%

    No Known Activations