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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tran
    -0.07
    /apis
    -0.07
     Nagar
    -0.07
     Antony
    -0.07
    .Notify
    -0.06
     keer
    -0.06
     dirname
    -0.06
     nguyện
    -0.06
     Grad
    -0.06
     propName
    -0.06
    POSITIVE LOGITS
    休息
    0.07
    щит
    0.07
    一个小
    0.07
    Hell
    0.07
    ListAdapter
    0.06
    $json
    0.06
    ✮
    0.06
     channelId
    0.06
    はない
    0.06
     Piece
    0.06
    Act Density 0.001%

    No Known Activations