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

    Neuronpedia

    INDEX
    Explanations

    supernovae and supernova explosions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    áció
    0.61
    á
    0.57
    ึก
    0.56
    він
    0.56
     ৭০
    0.55
     furtherance
    0.55
     deafness
    0.55
    ֵ
    0.55
     carène
    0.55
     optimisation
    0.54
    POSITIVE LOGITS
    ພວກເຮົາ
    0.84
    an
    0.79
     Kosovo
    0.75
    この
    0.74
    ພວກເຮ
    0.71
    Dieser
    0.71
    ب
    0.69
    ק
    0.68
     was
    0.68
    Pada
    0.67
    Act Density 0.002%

    No Known Activations