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

    Neuronpedia

    INDEX
    Explanations

    features and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     염
    0.71
    кновен
    0.70
    গুণ
    0.69
    🏿
    0.69
     মুগ্ধ
    0.68
    ß
    0.68
    ira
    0.66
    اقة
    0.66
    ynitrite
    0.66
    वर्ड
    0.65
    POSITIVE LOGITS
    ................
    1.21
    1.05
    0.97
    ----------------
    0.92
    ………………………………
    0.89
    ================
    0.89
    0.86
    0.86
    ...............
    0.84
                                
    0.83
    Act Density 0.015%

    No Known Activations