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

    Neuronpedia

    INDEX
    Explanations

    legal guilt and verdicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Extraordinary
    0.47
     글로벌
    0.43
     צו
    0.42
    Referensi
    0.41
     случай
    0.41
    大幅
    0.40
    系列
    0.40
    कृ
    0.40
    코
    0.40
    влека
    0.39
    POSITIVE LOGITS
     guilty
    0.71
     guilt
    0.54
     Guilty
    0.53
     culprit
    0.52
     culpable
    0.48
     fing
    0.47
     culpa
    0.46
     nodules
    0.46
    ingham
    0.46
     stained
    0.45
    Act Density 0.011%

    No Known Activations