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

    Neuronpedia

    INDEX
    Explanations

    jumps over the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$
    0.93
    ithin
    0.87
     )}$
    0.87
    েম্বর
    0.87
    وتن
    0.87
     }}$
    0.86
     зазна
    0.85
    ριν
    0.85
    عند
    0.84
    ैक्ट
    0.83
    POSITIVE LOGITS
     thunderstorms
    1.12
     cables
    0.93
     smashing
    0.90
     Margaret
    0.90
     accompanying
    0.88
     catalysts
    0.88
    یسم
    0.88
     прямой
    0.87
    став
    0.85
    стройство
    0.85
    Act Density 0.003%

    No Known Activations