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

    Neuronpedia

    INDEX
    Explanations

    typing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trú
    -0.06
    _corr
    -0.06
     appealing
    -0.06
     přím
    -0.06
    ين
    -0.06
     Cron
    -0.06
    沢
    -0.06
    -w
    -0.06
    mma
    -0.06
    _rsa
    -0.06
    POSITIVE LOGITS
     Packaging
    0.08
    *↵↵
    0.07
    /operator
    0.07
     자동
    0.07
    HITE
    0.06
     ValueType
    0.06
    #endregion
    0.06
     Byl
    0.06
     chef
    0.06
    (Type
    0.06
    Act Density 0.009%

    No Known Activations