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

    Neuronpedia

    INDEX
    Explanations

    code formatting and file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.52
     proportion
    0.45
     brand
    0.44
     ROY
    0.43
    惠
    0.43
     prep
    0.43
     look
    0.42
    ualitas
    0.42
     아주
    0.42
    anda
    0.41
    POSITIVE LOGITS
    glacial
    0.47
    㴬
    0.46
     dvara
    0.46
     hydrological
    0.46
    uerung
    0.45
    farande
    0.45
    ammlung
    0.45
     ദേശീയ
    0.45
    atedral
    0.45
    strlen
    0.44
    Act Density 0.011%

    No Known Activations