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

    Neuronpedia

    INDEX
    Explanations

    dual aspects or combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.23
    el
    1.18
    ي
    1.16
    ee
    1.09
    i
    1.09
     a
    1.08
    l
    1.04
    d
    1.01
    ü
    0.98
    de
    0.97
    POSITIVE LOGITS
    ς
    0.92
    ओं
    0.89
    (
    0.88
     competente
    0.87
     доба
    0.85
     perspectivas
    0.84
     connaissances
    0.83
     componente
    0.81
     rostro
    0.81
     один
    0.81
    Act Density 0.011%

    No Known Activations