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

    Neuronpedia

    INDEX
    Explanations

    skill ceiling, labor, resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konfer
    0.52
     narciss
    0.50
     obil
    0.48
     מו
    0.48
     Schwartz
    0.47
     narcissistic
    0.47
     כת
    0.46
     warrior
    0.46
     אנ
    0.46
     Зак
    0.46
    POSITIVE LOGITS
    ла
    0.60
    時間
    0.49
    та
    0.49
    ники
    0.48
    дь
    0.47
    提供
    0.46
    ры
    0.46
    ств
    0.46
    促
    0.46
    ená
    0.45
    Act Density 0.000%

    No Known Activations