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

    Neuronpedia

    INDEX
    Explanations

    say "By"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bry
    0.44
     Bryson
    0.43
     bry
    0.42
    వ్య
    0.40
     Lyon
    0.40
    EndY
    0.40
    cY
    0.40
    枒
    0.40
    oly
    0.39
    EDY
    0.39
    POSITIVE LOGITS
     ABOUT
    0.45
    相対
    0.43
     relative
    0.40
     relativ
    0.38
    点を
    0.38
     상대
    0.38
    ліз
    0.37
    RELATIVE
    0.37
     neurons
    0.36
    ｍｍ
    0.36
    Act Density 0.000%

    No Known Activations