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

    Neuronpedia

    INDEX
    Explanations

    losing privileges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medic
    -0.09
    -weight
    -0.07
    ORIES
    -0.07
     broadly
    -0.06
    وین
    -0.06
     rodi
    -0.06
     disp
    -0.06
     EVAL
    -0.06
    ?f
    -0.06
    bps
    -0.06
    POSITIVE LOGITS
    .results
    0.07
    estruct
    0.07
     DBG
    0.06
    monster
    0.06
    (strip
    0.06
    (draw
    0.06
     raced
    0.06
    .setViewport
    0.06
    idad
    0.06
    (parser
    0.06
    Act Density 0.041%

    No Known Activations