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

    Neuronpedia

    INDEX
    Explanations

    Later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Res
    -0.07
    ,and
    -0.07
    _IM
    -0.07
    塑胶
    -0.07
    /manage
    -0.07
     Öl
    -0.07
     Formal
    -0.07
     angst
    -0.07
    Resolve
    -0.06
     businessman
    -0.06
    POSITIVE LOGITS
     uploader
    0.08
    땟
    0.07
     כתובת
    0.07
    𒁺
    0.06
     הרב
    0.06
    ציג
    0.06
    备份
    0.06
    	ptr
    0.06
    鲣
    0.06
    转载请
    0.06
    Act Density 0.023%

    No Known Activations