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

    Neuronpedia

    INDEX
    Explanations

    expert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rani
    -0.07
     評価
    -0.06
    dot
    -0.06
    DirectoryName
    -0.06
    hours
    -0.06
     Ø
    -0.06
     �
    -0.06
    äter
    -0.06
     pled
    -0.06
     ik
    -0.06
    POSITIVE LOGITS
    Styled
    0.07
    uitive
    0.06
     بسي
    0.06
     Elevated
    0.06
    щей
    0.06
     разв
    0.06
     spring
    0.06
     کرد
    0.06
    зация
    0.05
     вит
    0.05
    Act Density 0.012%

    No Known Activations