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

    Neuronpedia

    INDEX
    Explanations

    Start and end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лом
    -0.07
    高的
    -0.07
     davon
    -0.07
    -star
    -0.07
     Windows
    -0.07
    обесп
    -0.07
     vida
    -0.06
    (lambda
    -0.06
     timeStamp
    -0.06
     window
    -0.06
    POSITIVE LOGITS
    _rec
    0.07
     Пос
    0.07
    _invalid
    0.06
     excerpt
    0.06
     circumcision
    0.06
    DECREF
    0.06
    给予
    0.06
     rec
    0.06
     Eğ
    0.06
    ပ
    0.06
    Act Density 0.048%

    No Known Activations