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

    Neuronpedia

    INDEX
    Explanations

    murdered, killed, abducted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lanjutkan
    0.81
    Maintaining
    0.66
    oea
    0.65
     পদার্থের
    0.65
    Males
    0.64
    同步
    0.64
     NSURL
    0.64
     쉽
    0.63
    гүй
    0.62
     שלא
    0.61
    POSITIVE LOGITS
     murdered
    2.43
     killed
    2.35
     kidnapped
    2.04
     assassinated
    1.96
     murdering
    1.83
     abducted
    1.82
     Killed
    1.82
    killed
    1.76
     slaughtered
    1.73
     stabbed
    1.71
    Act Density 0.096%

    No Known Activations