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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roomId
    -0.07
     Party
    -0.06
     homosex
    -0.06
     voxel
    -0.06
     jes
    -0.06
    รรค
    -0.06
    Insurance
    -0.06
     Inst
    -0.06
     협
    -0.06
    ','#
    -0.06
    POSITIVE LOGITS
     HW
    0.07
     Electrical
    0.06
    ..."↵↵
    0.06
     Phillip
    0.06
     tbl
    0.06
    bsd
    0.06
     khiến
    0.06
     sonucu
    0.06
     unwitting
    0.06
    _tbl
    0.06
    Act Density 0.023%

    No Known Activations