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

    Neuronpedia

    INDEX
    Explanations

    computer information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ആ
    0.52
     ആ
    0.50
     cycle
    0.49
     snorkel
    0.46
     Dlatego
    0.46
     heure
    0.45
    Precio
    0.45
     Precio
    0.44
     rate
    0.44
     Selector
    0.44
    POSITIVE LOGITS
    s
    0.48
    parsed
    0.46
     atthakath
    0.45
    IMAGES
    0.45
    brad
    0.45
    找到
    0.44
    信息
    0.44
    linhas
    0.44
    wchar
    0.44
    lsen
    0.43
    Act Density 0.001%

    No Known Activations