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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ανα
    -0.06
     ortadan
    -0.06
    _activate
    -0.06
    лов
    -0.06
     залиш
    -0.06
     норм
    -0.06
    �
    -0.06
    etermine
    -0.06
     degradation
    -0.06
    <_
    -0.06
    POSITIVE LOGITS
    اسي
    0.08
     skeleton
    0.08
    .InvariantCulture
    0.07
    �
    0.07
    (numbers
    0.07
     liquidity
    0.06
     th
    0.06
    -dialog
    0.06
    Steve
    0.06
    视频
    0.06
    Act Density 0.000%

    No Known Activations