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

    Neuronpedia

    INDEX
    Explanations

    más brutal, without having

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Teddy
    0.42
     ٹرسٹ
    0.39
    ственную
    0.39
    べて
    0.39
     Jennings
    0.38
    туи
    0.38
    全体
    0.37
     Withdrawal
    0.37
     तेज़
    0.37
     Bronco
    0.37
    POSITIVE LOGITS
    र्वेद
    0.40
    ःख
    0.38
    NSMutable
    0.38
    Wh
    0.37
    cls
    0.37
     née
    0.37
    фр
    0.36
    exercice
    0.36
     chirp
    0.36
     ado
    0.35
    Act Density 0.000%

    No Known Activations