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

    Neuronpedia

    INDEX
    Explanations

    to hear or see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suffices
    0.90
    หรือ
    0.89
     vagy
    0.86
     లేదా
    0.86
     شدند
    0.84
     uygun
    0.84
     เพิ่ม
    0.82
     또는
    0.80
     alebo
    0.79
     przeciw
    0.79
    POSITIVE LOGITS
     be
    1.71
     hear
    1.65
     have
    1.42
     admit
    1.33
     know
    1.26
     acknowledge
    1.25
     think
    1.20
     realize
    1.18
     witness
    1.14
     see
    1.13
    Act Density 0.059%

    No Known Activations