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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jh
    -0.07
    _var
    -0.07
    회
    -0.07
    qb
    -0.07
    एस
    -0.06
    med
    -0.06
    ›
    -0.06
     Week
    -0.06
     двер
    -0.06
    吧
    -0.06
    POSITIVE LOGITS
    $input
    0.06
     مقاو
    0.06
    .FloatField
    0.06
    　V
    0.06
     Amendments
    0.06
     garant
    0.06
     cudaMemcpy
    0.06
     تلویزی
    0.06
    -volume
    0.06
     grading
    0.06
    Act Density 0.015%

    No Known Activations