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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأكثر
    -0.08
    .Bundle
    -0.07
    езн
    -0.07
     swimming
    -0.07
    URRENCY
    -0.07
    眼球
    -0.07
    عقد
    -0.07
     especialmente
    -0.07
    ♀
    -0.07
    ﾞ
    -0.07
    POSITIVE LOGITS
     Richmond
    0.07
    _consumer
    0.07
    Remember
    0.07
    aad
    0.07
    /usr
    0.07
    aa
    0.07
    inka
    0.07
     ipt
    0.06
     /\
    0.06
    Processed
    0.06
    Act Density 0.200%

    No Known Activations