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

    Neuronpedia

    INDEX
    Explanations

    penalties for killing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    فرج
    0.44
     slander
    0.43
    ASX
    0.42
    icast
    0.42
    饰演
    0.42
    ेश्वरी
    0.42
    违法
    0.41
     subtitles
    0.41
    🎿
    0.40
    wiches
    0.40
    POSITIVE LOGITS
     scale
    0.40
     kg
    0.40
     প্রাপ্ত
    0.39
     মৃত্যু
    0.38
     தமிழக
    0.38
     kill
    0.38
     slayer
    0.38
     assassins
    0.37
    殺
    0.37
    基準
    0.36
    Act Density 0.013%

    No Known Activations