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

    Neuronpedia

    INDEX
    Explanations

    without this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تين
    0.87
    ควร
    0.84
    DP
    0.84
    ೇ
    0.84
     ہے۔
    0.83
    குழந்த
    0.83
    았습니다
    0.83
    楂
    0.82
    璘
    0.82
    OF
    0.81
    POSITIVE LOGITS
     else
    0.88
     μια
    0.81
     назем
    0.81
    unavailable
    0.79
     gasto
    0.77
     طبعا
    0.77
    ektiv
    0.75
     එව
    0.75
    nosi
    0.75
    etku
    0.74
    Act Density 0.068%

    No Known Activations