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

    Neuronpedia

    INDEX
    Explanations

    Scientists estimate or believe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    据
    0.85
     berichtet
    0.82
     сообщил
    0.82
     exigir
    0.77
    についても
    0.74
     behaupt
    0.74
     сказала
    0.73
    बताया
    0.73
     estableció
    0.72
     bluntly
    0.72
    POSITIVE LOGITS
    શા
    0.88
     drie
    0.75
    ﺒ
    0.74
     LCA
    0.73
     from
    0.73
    分為
    0.72
    หลากหลาย
    0.72
     diag
    0.70
     I
    0.69
     Lumen
    0.68
    Act Density 0.007%

    No Known Activations