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

    Neuronpedia

    INDEX
    Explanations

    written communications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (device
    -0.07
    rypted
    -0.07
    HF
    -0.07
     области
    -0.06
     LSTM
    -0.06
    _proc
    -0.06
     Pen
    -0.06
    OTE
    -0.06
    forecast
    -0.06
     FIFO
    -0.06
    POSITIVE LOGITS
     setTitleColor
    0.07
    "These
    0.06
    (decoded
    0.06
     tổn
    0.06
    оратив
    0.06
     Temmuz
    0.06
    ?<
    0.06
    พระราช
    0.06
     Game
    0.06
    ература
    0.06
    Act Density 0.048%

    No Known Activations