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

    Neuronpedia

    INDEX
    Explanations

    link href/rel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Know
    0.41
    衆
    0.39
     KNOW
    0.39
    arguments
    0.38
    Know
    0.38
     கலோரிகள்
    0.38
     項
    0.36
     جانا
    0.36
    項
    0.36
    ENDER
    0.36
    POSITIVE LOGITS
    筛
    0.43
     unidad
    0.38
    갱
    0.37
     awesome
    0.37
    cosity
    0.37
    лость
    0.36
     amyloid
    0.35
     rats
    0.35
    ません
    0.35
     incredibly
    0.35
    Act Density 0.001%

    No Known Activations