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

    Neuronpedia

    INDEX
    Explanations

    languages: or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EVERYTHING
    0.54
     everything
    0.49
     BOTH
    0.49
     ALL
    0.48
     somewhat
    0.46
    ங்களும்
    0.43
     تقريبا
    0.43
     three
    0.43
     mainly
    0.43
     approx
    0.43
    POSITIVE LOGITS
     किंवा
    0.73
     или
    0.70
     veya
    0.67
     vagy
    0.63
     లేదా
    0.63
     hoặc
    0.62
     ataupun
    0.61
     oder
    0.61
     alebo
    0.60
    或者
    0.59
    Act Density 0.205%

    No Known Activations