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

    Neuronpedia

    INDEX
    Explanations

    updated status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istä
    1.86
    AndUpdate
    1.62
    Karena
    1.53
    $('#
    1.52
    étend
    1.49
    ות
    1.48
    Ν
    1.48
     ơn
    1.45
    Ông
    1.45
    き
    1.44
    POSITIVE LOGITS
     altres
    2.03
     delgado
    1.95
     suave
    1.90
    ेक्षित
    1.81
    ेक्षा
    1.73
     quantos
    1.73
     provoqu
    1.71
     vistas
    1.70
     requisitos
    1.69
     وفي
    1.67
    Act Density 0.417%

    No Known Activations