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

    Neuronpedia

    INDEX
    Explanations

    defining murder and its legality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.12
    س
    1.12
    は
    1.08
    م
    1.06
     is
    1.03
    ના
    1.02
    和他
    0.98
     और
    0.97
    ۔
    0.97
    是
    0.96
    POSITIVE LOGITS
    <0x0D>
    1.08
     murdering
    0.96
     asesinato
    0.86
     murder
    0.83
    cemia
    0.83
    of
    0.82
     assemblages
    0.81
    ர்
    0.80
     homicide
    0.80
    </td>
    0.79
    Act Density 0.003%

    No Known Activations