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

    Neuronpedia

    INDEX
    Explanations

    been long

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     m
    0.61
     ty
    0.60
    불
    0.59
    |
    0.57
    urahan
    0.57
    bt
    0.57
    říve
    0.56
    tty
    0.56
    jár
    0.56
     normale
    0.55
    POSITIVE LOGITS
     relegation
    0.96
    郦
    0.90
     acoustics
    0.87
    ड़ों
    0.86
     pipa
    0.85
     हैद
    0.84
     presion
    0.83
     retaliation
    0.82
     һ
    0.82
     propósito
    0.82
    Act Density 0.024%

    No Known Activations