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

    Neuronpedia

    INDEX
    Explanations

    file reading and HTTP requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .viewModel
    -0.07
     Bristol
    -0.07
    .status
    -0.07
     이야기
    -0.07
    split
    -0.07
     Coin
    -0.07
     politely
    -0.07
    Spec
    -0.07
     wurden
    -0.06
     thieves
    -0.06
    POSITIVE LOGITS
    貼
    0.06
     얼
    0.06
     rem
    0.06
     základ
    0.06
    ******/
    0.06
     fotos
    0.06
    ráž
    0.06
    Urls
    0.06
    ज
    0.06
    -comp
    0.06
    Act Density 0.051%

    No Known Activations