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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    öl
    -0.07
     shar
    -0.07
     lofty
    -0.07
     변경
    -0.06
     chức
    -0.06
    Tel
    -0.06
     Verification
    -0.06
    ทอง
    -0.06
    datal
    -0.06
     přeb
    -0.06
    POSITIVE LOGITS
    .pattern
    0.06
    іс
    0.06
    	Game
    0.06
     horrific
    0.06
     Birds
    0.06
    _beta
    0.06
    :relative
    0.06
    ysz
    0.06
    (ev
    0.06
    ICK
    0.06
    Act Density 0.014%

    No Known Activations