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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     možnost
    0.75
     Ainda
    0.73
     Due
    0.73
     अत्यंत
    0.73
     పూర్తిగా
    0.72
     నాకు
    0.72
     कृपया
    0.71
    foration
    0.70
     ยัง
    0.70
     There
    0.70
    POSITIVE LOGITS
     sayings
    0.79
     bills
    0.77
     dragons
    0.76
     larvae
    0.74
     money
    0.72
     zombies
    0.72
     poems
    0.71
     vampires
    0.71
     successes
    0.71
     verbs
    0.70
    Act Density 0.265%

    No Known Activations