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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ассив
    -0.07
    anian
    -0.06
    achelor
    -0.06
    .marker
    -0.06
    .WebElement
    -0.06
    ius
    -0.06
    arker
    -0.06
    engan
    -0.06
    зем
    -0.06
    акс
    -0.06
    POSITIVE LOGITS
    Ě
    0.07
     Virtual
    0.07
     ал
    0.07
     eval
    0.07
    熊
    0.07
    �
    0.07
     θέ
    0.07
    _discount
    0.06
     while
    0.06
    Whilst
    0.06
    Act Density 0.023%

    No Known Activations