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

    Neuronpedia

    INDEX
    Explanations

    harm, loss, or death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uyorum
    0.75
    z
    0.72
    о
    0.70
     wiggle
    0.70
     attualmente
    0.69
    borhood
    0.68
     yogurt
    0.68
     പുതിയ
    0.68
    Puedes
    0.67
    ப்பட்டி
    0.67
    POSITIVE LOGITS
     perished
    1.03
     করেছিল
    0.91
     Opfer
    0.84
     victime
    0.79
     Fatal
    0.78
     victimes
    0.76
     suffered
    0.75
    thisTrack
    0.75
     succumbed
    0.73
     столь
    0.73
    Act Density 0.005%

    No Known Activations