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

    Neuronpedia

    INDEX
    Explanations

    code block endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    0.67
    Platform
    0.61
     Συν
    0.59
     seiner
    0.57
     그는
    0.56
     plateforme
    0.56
    Lago
    0.55
    ISSN
    0.54
     trunk
    0.54
    Break
    0.54
    POSITIVE LOGITS
     দেওয়ার
    0.62
     метода
    0.61
     দেওয়ার
    0.57
    ()))
    0.57
     método
    0.56
    ଲେ
    0.55
    roft
    0.55
     Hodge
    0.55
    ()
    0.54
     walks
    0.54
    Act Density 0.011%

    No Known Activations