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

    Neuronpedia

    INDEX
    Explanations

    explaining data points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PA
    0.52
    ES
    0.49
     Lernen
    0.46
    OMAS
    0.46
    PAUL
    0.46
    png
    0.46
    SB
    0.45
    Š
    0.45
    BA
    0.44
     produkty
    0.44
    POSITIVE LOGITS
    رى
    0.54
    ളാ
    0.48
    ssä
    0.47
    alay
    0.46
    usiasm
    0.45
    syair
    0.45
     yù
    0.45
    encji
    0.44
     ஆடி
    0.44
    ری
    0.43
    Act Density 0.001%

    No Known Activations