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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Numer
    -0.07
     kapat
    -0.06
     책
    -0.06
    ульт
    -0.06
     Prototype
    -0.06
     chiefly
    -0.06
     calloc
    -0.06
    Different
    -0.06
     Peg
    -0.06
    =-=-=-=-=-=-=-=-
    -0.06
    POSITIVE LOGITS
     strpos
    0.07
     digs
    0.06
    _TypeInfo
    0.06
     passages
    0.06
     corpus
    0.06
     pdo
    0.06
    lov
    0.06
     resetting
    0.06
     passage
    0.06
     дії
    0.06
    Act Density 0.006%

    No Known Activations