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

    Neuronpedia

    INDEX
    Explanations

    list indices and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વ્યવ
    0.38
    parseFloat
    0.38
    еш
    0.38
    ходя
    0.36
    ℞
    0.36
    ાદ
    0.36
     evaluación
    0.36
    дных
    0.36
    ⁡
    0.36
    ̳
    0.36
    POSITIVE LOGITS
     ০
    0.47
     IndexPath
    0.41
     cohort
    0.39
     Coh
    0.38
     absc
    0.37
     Indices
    0.36
    startIndex
    0.36
    ].
    0.36
     inclusive
    0.34
    indices
    0.34
    Act Density 0.059%

    No Known Activations