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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Пр
    -0.06
    _hierarchy
    -0.06
     रहन
    -0.06
    Jak
    -0.06
     ساده
    -0.06
    Route
    -0.06
     Пр
    -0.06
    (skip
    -0.06
    >P
    -0.06
     hammer
    -0.05
    POSITIVE LOGITS
    イズ
    0.07
     PERFORMANCE
    0.07
     becomes
    0.06
    ComputedStyle
    0.06
    _bo
    0.06
    vida
    0.06
    ulary
    0.06
    fal
    0.06
     noh
    0.06
     čtvrt
    0.06
    Act Density 0.133%

    No Known Activations