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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отнош
    -0.07
     ра
    -0.07
    negative
    -0.07
    ader
    -0.06
    enne
    -0.06
    _viewer
    -0.06
     tamp
    -0.06
    Selective
    -0.06
    pseudo
    -0.06
     phiếu
    -0.06
    POSITIVE LOGITS
    =k
    0.07
     چیز
    0.06
    .uint
    0.06
    ीज
    0.06
    	point
    0.06
    静
    0.06
     нія
    0.06
     клас
    0.06
    เมตร
    0.06
     meds
    0.06
    Act Density 0.055%

    No Known Activations