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

    Neuronpedia

    INDEX
    Explanations

    join(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stomach
    0.65
     &
    0.61
     প্রোগ্র
    0.57
     Alternatively
    0.57
     If
    0.55
     মেরে
    0.55
     Since
    0.53
    ']}")
    0.53
     Applications
    0.52
     किसको
    0.52
    POSITIVE LOGITS
    น
    0.89
    т
    0.80
    ي
    0.77
    ни
    0.76
    ر
    0.74
    тет
    0.73
    us
    0.70
    u
    0.70
    ن
    0.69
     प्रकारचे
    0.68
    Act Density 0.018%

    No Known Activations