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

    Neuronpedia

    INDEX
    Explanations

    transfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )'),↵
    -0.07
    пряжен
    -0.07
     ignition
    -0.07
    tokenId
    -0.07
     seinen
    -0.06
    なの
    -0.06
    "),↵
    -0.06
    足足
    -0.06
    QObject
    -0.06
    portal
    -0.06
    POSITIVE LOGITS
    	ext
    0.09
    受影响
    0.07
    Textbox
    0.07
    -that
    0.06
    _conf
    0.06
     RJ
    0.06
     Paper
    0.06
    (output
    0.06
    *out
    0.06
    決定
    0.06
    Act Density 0.002%

    No Known Activations