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

    Neuronpedia

    INDEX
    Explanations

    violent actions, death, resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.98
    ↵
    0.82
    of
    0.77
    ad
    0.76
    न
    0.70
    -
    0.68
    ון
    0.65
    ة
    0.65
    6
    0.65
    PI
    0.64
    POSITIVE LOGITS
    ित
    0.92
    ت
    0.85
    ي
    0.78
    ្នែក
    0.75
    تص
    0.73
    י
    0.73
     There
    0.71
     Offences
    0.71
    твы
    0.71
    ত
    0.71
    Act Density 0.000%

    No Known Activations