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

    Neuronpedia

    INDEX
    Explanations

    common language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getS
    -0.07
     Пол
    -0.07
    _NR
    -0.07
     Ph
    -0.07
     altern
    -0.07
     Ev
    -0.06
     Amount
    -0.06
    _building
    -0.06
     openness
    -0.06
     Palmer
    -0.06
    POSITIVE LOGITS
    артам
    0.07
    도를
    0.07
    Submitting
    0.06
    =req
    0.06
     této
    0.06
     TORT
    0.06
    (logger
    0.06
     edilmiştir
    0.06
    çok
    0.06
    .now
    0.06
    Act Density 0.181%

    No Known Activations