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

    Neuronpedia

    INDEX
    Explanations

    thank you and polite acknowledgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hasil
    0.80
    Hãy
    0.77
     життя
    0.72
     Hãy
    0.71
    عهد
    0.71
    തെന്ന്
    0.71
     उत
    0.70
     باي
    0.70
    ┣
    0.70
    ąć
    0.69
    POSITIVE LOGITS
     great
    0.95
     interesting
    0.90
     perfect
    0.88
     Interesting
    0.87
     noted
    0.86
     fascinating
    0.82
     well
    0.80
     excellent
    0.79
     Perfect
    0.78
     understood
    0.78
    Act Density 0.289%

    No Known Activations