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

    Neuronpedia

    INDEX
    Explanations

    explicitly stated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    0.95
    g
    0.82
    kannya
    0.70
    making
    0.69
     the
    0.68
    да
    0.68
    こと
    0.66
     their
    0.66
     वसू
    0.65
     costo
    0.65
    POSITIVE LOGITS
    на
    0.97
    сть
    0.94
    но
    0.88
    л
    0.85
    व
    0.84
    ні
    0.81
    as
    0.80
    ть
    0.79
    ா
    0.78
    вання
    0.76
    Act Density 1.336%

    No Known Activations