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

    Neuronpedia

    INDEX
    Explanations

    how and why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ipelago
    0.40
     excl
    0.38
    (`${
    0.37
    ሏ
    0.37
    ilizce
    0.36
     ऑपरेट
    0.36
    ల్‌
    0.35
    ಸ್‌
    0.35
     svært
    0.34
     desta
    0.34
    POSITIVE LOGITS
     how
    0.90
    如何
    0.83
     如何
    0.81
     why
    0.80
     bagaimana
    0.80
     overcoming
    0.79
     importance
    0.78
     কিভাবে
    0.75
     importância
    0.75
    why
    0.73
    Act Density 0.015%

    No Known Activations