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

    Neuronpedia

    INDEX
    Explanations

    has/have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mantle
    -0.07
     flair
    -0.07
    plotlib
    -0.07
    ewish
    -0.06
     applicationContext
    -0.06
     Raq
    -0.06
     COPYING
    -0.06
    ιστη
    -0.06
    -frequency
    -0.06
    FirstResponder
    -0.06
    POSITIVE LOGITS
    _true
    0.06
     موتور
    0.06
    ZERO
    0.06
    Ordinal
    0.06
     Мат
    0.06
    intros
    0.06
    เฮ
    0.06
     delays
    0.06
     Gr
    0.06
    _Normal
    0.06
    Act Density 0.038%

    No Known Activations