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

    Neuronpedia

    INDEX
    Explanations

    explaining clarifying help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സൃഷ്ട
    0.45
     suggestions
    0.42
    Suggestions
    0.41
    実装
    0.41
     Suggestions
    0.40
     inspirations
    0.39
     вдох
    0.39
     پیشنه
    0.39
     노력
    0.39
     recibirá
    0.39
    POSITIVE LOGITS
     clarifies
    0.89
     esclare
    0.86
     wyja
    0.85
     explain
    0.83
     explains
    0.82
     объяс
    0.82
     clarify
    0.79
     explanation
    0.77
     explaining
    0.77
     clarifying
    0.77
    Act Density 0.001%

    No Known Activations