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

    Neuronpedia

    INDEX
    Explanations

    developer tools and aesthetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exuber
    0.42
     subjug
    0.41
     quell
    0.40
     zare
    0.39
     futile
    0.39
     saison
    0.39
     novos
    0.39
     benevolence
    0.39
     solace
    0.38
     lauf
    0.38
    POSITIVE LOGITS
    রি
    0.45
     전문가
    0.43
    padding
    0.43
    ଜ
    0.42
    ଣ୍
    0.41
    <0x9A>
    0.40
    άζ
    0.39
    ছোট
    0.38
    akkhati
    0.38
    ει
    0.38
    Act Density 0.170%

    No Known Activations