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

    Neuronpedia

    INDEX
    Explanations

    se

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ladık
    -0.07
     яких
    -0.07
    -0.07
    negative
    -0.06
    ),
    -0.06
    (contact
    -0.06
     hale
    -0.06
    ंघ
    -0.06
    eneration
    -0.06
    frared
    -0.06
    POSITIVE LOGITS
     pen
    0.08
     supervision
    0.06
    bitmap
    0.06
     DISP
    0.06
     collaboration
    0.06
     봉
    0.06
     Pen
    0.06
    ouch
    0.06
     heritage
    0.06
     Months
    0.06
    Act Density 0.005%

    No Known Activations