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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instead
    0.59
     constant
    0.57
     rather
    0.57
     anyway
    0.57
     poor
    0.57
     video
    0.56
     minimum
    0.56
     older
    0.55
    वीय
    0.55
     constantly
    0.55
    POSITIVE LOGITS
     vuelta
    0.79
     regreso
    0.78
     Бушлай
    0.77
    ீஸ்
    0.74
     Букмекерлар
    0.74
     Respublik
    0.72
     ലീ
    0.72
     ریا
    0.72
    ukuran
    0.72
    bia
    0.72
    Act Density 0.399%

    No Known Activations