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
    Keywords
    -0.07
     слова
    -0.07
     INT
    -0.07
    ”的
    -0.07
     chin
    -0.07
     laid
    -0.07
     AT
    -0.07
    Foot
    -0.07
     focus
    -0.06
     fluoride
    -0.06
    POSITIVE LOGITS
    .viewModel
    0.07
    ávající
    0.07
     Deadpool
    0.07
     Dipl
    0.06
    roles
    0.06
     позвол
    0.06
     Making
    0.06
    awy
    0.06
    Repositories
    0.06
     Pred
    0.06
    Act Density 0.017%

    No Known Activations