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

    Neuronpedia

    INDEX
    Explanations

    comprehensive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.70
    sl
    0.63
     ļ
    0.62
    v
    0.60
    ли
    0.56
    et
    0.55
    o
    0.54
     গৌরব
    0.54
     lindos
    0.52
    掙
    0.52
    POSITIVE LOGITS
    י
    0.86
    ي
    0.78
    i
    0.72
    पणे
    0.70
     comprehensive
    0.69
     Comprehensive
    0.68
     کامل
    0.66
    ності
    0.64
    iéndose
    0.63
    全面
    0.62
    Act Density 0.051%

    No Known Activations