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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    投保
    -0.07
    setCurrent
    -0.07
    clc
    -0.07
    MONTH
    -0.07
    .addAction
    -0.06
    薜
    -0.06
     fear
    -0.06
    pects
    -0.06
    嚏
    -0.06
     winnings
    -0.06
    POSITIVE LOGITS
    פול
    0.07
    רית
    0.07
    	es
    0.07
    再现
    0.06
     EH
    0.06
    اف
    0.06
    /output
    0.06
    ใหม
    0.06
    花纹
    0.06
    PM
    0.06
    Act Density 0.002%

    No Known Activations