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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     causing
    -0.08
     büyük
    -0.07
    アップ
    -0.07
     keeping
    -0.07
     pools
    -0.07
     kitap
    -0.07
     있던
    -0.07
     Metal
    -0.06
     sempre
    -0.06
     YEARS
    -0.06
    POSITIVE LOGITS
     isConnected
    0.06
     getOrder
    0.06
    elong
    0.06
    )을
    0.06
    Acc
    0.06
    .UserService
    0.06
    emales
    0.06
    ues
    0.06
     putt
    0.06
     ettiği
    0.06
    Act Density 0.031%

    No Known Activations