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

    Neuronpedia

    INDEX
    Explanations

    comparisons and prevalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    In
    -0.09
     In
    -0.07
     Rising
    -0.07
    _IN
    -0.07
    _In
    -0.07
     stato
    -0.07
     becomes
    -0.07
    Lat
    -0.06
     becoming
    -0.06
     पर
    -0.06
    POSITIVE LOGITS
    (vc
    0.06
    ảnh
    0.06
    pressor
    0.06
    .VERSION
    0.06
    働
    0.06
     racket
    0.06
     [~,
    0.06
    conti
    0.06
     خیلی
    0.06
    iềm
    0.06
    Act Density 0.134%

    No Known Activations