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

    Neuronpedia

    INDEX
    Explanations

    home vs guest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ɱ
    1.01
     zbog
    0.89
    BAC
    0.88
    us
    0.88
     temperament
    0.86
    ɴ
    0.84
    ledged
    0.84
     آف
    0.84
    VEMENT
    0.82
     сказать
    0.82
    POSITIVE LOGITS
    ся
    0.95
    दारा
    0.94
     wedstrij
    0.93
     Grizzlies
    0.88
    n
    0.87
    getEntity
    0.85
    скоре
    0.84
    0.84
     hysteresis
    0.84
    y
    0.83
    Act Density 0.024%

    No Known Activations