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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ьи
    -0.07
     pian
    -0.07
     awarded
    -0.07
     commodities
    -0.06
     ناح
    -0.06
     representa
    -0.06
    esta
    -0.06
    GBT
    -0.06
     games
    -0.06
     correspond
    -0.06
    POSITIVE LOGITS
     miles
    0.07
    ,content
    0.07
    decltype
    0.06
     Chapter
    0.06
     DataService
    0.06
    سم
    0.06
    Firefox
    0.06
    .Root
    0.06
    _Style
    0.06
    (`<
    0.06
    Act Density 0.026%

    No Known Activations