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

    Neuronpedia

    INDEX
    Explanations

    f followed by "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     œuvre
    0.86
     ジュ
    0.81
     י
    0.81
     пор
    0.77
     Dong
    0.75
     công
    0.74
     PowerPoint
    0.74
     Myst
    0.73
     গুণে
    0.72
    supers
    0.72
    POSITIVE LOGITS
    "
    0.73
    Allow
    0.70
    Academic
    0.68
     শত্র
    0.67
    Who
    0.67
    leyebilirsiniz
    0.66
    '
    0.65
    nunique
    0.64
    who
    0.63
    椒
    0.63
    Act Density 0.039%

    No Known Activations