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

    Neuronpedia

    INDEX
    Explanations

    prohibiting violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मधील
    0.46
    ių
    0.44
     sAlarm
    0.43
     sniping
    0.42
     doğr
    0.41
     मिनिस्टर
    0.40
     المحاضره
    0.40
     সরল
    0.39
     кислоты
    0.39
     physiologique
    0.39
    POSITIVE LOGITS
     erupt
    0.50
    对
    0.47
    ad
    0.43
    professional
    0.43
    Viol
    0.42
    нора
    0.42
    奋
    0.42
     violently
    0.41
    暴
    0.39
     doméstica
    0.39
    Act Density 0.008%

    No Known Activations