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

    Neuronpedia

    INDEX
    Explanations

    OK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convivial
    0.41
     adicionales
    0.41
     diferentes
    0.40
     discretionary
    0.39
     conoz
    0.38
     atividades
    0.38
     relatable
    0.38
     sejumlah
    0.38
     Noticias
    0.38
     farklı
    0.37
    POSITIVE LOGITS
     miserably
    0.44
    oretically
    0.43
     உண்
    0.42
    假設
    0.41
    infty
    0.40
    óstico
    0.40
    onycha
    0.39
    ass
    0.39
    Assuming
    0.39
    vì
    0.39
    Act Density 0.035%

    No Known Activations