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

    Neuronpedia

    INDEX
    Explanations

    orph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    得天
    -0.07
     materials
    -0.07
     meetings
    -0.07
    ảy
    -0.07
     nal
    -0.07
     دق
    -0.07
     nok
    -0.06
    涨
    -0.06
    liced
    -0.06
    姜
    -0.06
    POSITIVE LOGITS
    ﭕ
    0.08
    儒
    0.08
    其实是
    0.07
    Clr
    0.07
    поз
    0.06
    -null
    0.06
    mans
    0.06
    \Auth
    0.06
     floats
    0.06
    predict
    0.06
    Act Density 0.010%

    No Known Activations