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

    Neuronpedia

    INDEX
    Explanations

    CEO, she, shadow, loyalty, sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <td>
    0.52
     ö
    0.52
    enable
    0.51
    ibly
    0.48
     رياض
    0.48
    itin
    0.48
    lend
    0.48
    elt
    0.48
     Št
    0.48
    },
    0.47
    POSITIVE LOGITS
    ส
    0.52
    Discord
    0.48
    ドラゴン
    0.47
     Sociology
    0.47
    ์
    0.47
    ق
    0.47
     hostage
    0.46
    वारा
    0.45
    ผู้
    0.45
     Nursing
    0.45
    Act Density 0.000%

    No Known Activations