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

    Neuronpedia

    INDEX
    Explanations

    Location or state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certificates
    -0.07
    Detect
    -0.07
     курс
    -0.06
     rebel
    -0.06
     typeId
    -0.06
    危
    -0.06
    _pitch
    -0.06
    ouncing
    -0.06
    _disk
    -0.06
     عنوان
    -0.06
    POSITIVE LOGITS
    iley
    0.06
     "**
    0.06
     Beer
    0.06
     раб
    0.06
    (LL
    0.06
    ộ
    0.06
    rogram
    0.06
     cevap
    0.06
    (/*
    0.06
    mutation
    0.06
    Act Density 0.054%

    No Known Activations