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

    Neuronpedia

    INDEX
    Explanations

    Figures with exaggerated elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saves
    -0.07
     Brett
    -0.07
     involves
    -0.07
     �
    -0.06
    _CLIP
    -0.06
    excluding
    -0.06
    Avoid
    -0.06
     eles
    -0.06
     Lack
    -0.06
    problems
    -0.06
    POSITIVE LOGITS
    .swift
    0.07
    τής
    0.06
     voter
    0.06
    宽
    0.06
     mutated
    0.06
    ование
    0.06
    ักษณ
    0.06
    //************************************************************************
    0.06
    ogene
    0.06
     specify
    0.06
    Act Density 0.003%

    No Known Activations