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

    Neuronpedia

    INDEX
    Explanations

    integral of functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    3.20
    า
    3.04
    ो
    2.91
    ة
    2.18
    el
    2.01
    ोम
    1.91
    et
    1.85
    ר
    1.84
    هه
    1.81
    ることが
    1.78
    POSITIVE LOGITS
    푼
    1.80
     arro
    1.74
    buscador
    1.66
    acios
    1.61
     усили
    1.60
    ب
    1.58
     muhimu
    1.56
     concep
    1.55
     anuv
    1.55
    crs
    1.55
    Act Density 0.002%

    No Known Activations