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

    Neuronpedia

    INDEX
    Explanations

    harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dung
    -0.07
     appropri
    -0.07
     main
    -0.07
    …..
    -0.06
    (contents
    -0.06
    Output
    -0.06
     errorMsg
    -0.06
    嗉
    -0.06
     unloaded
    -0.06
     duro
    -0.06
    POSITIVE LOGITS
    getParam
    0.07
    RICT
    0.07
    _RES
    0.06
    举
    0.06
    면
    0.06
    [list
    0.06
     Signal
    0.06
    .rmtree
    0.06
    职业生涯
    0.06
    갔
    0.06
    Act Density 0.044%

    No Known Activations