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

    Neuronpedia

    INDEX
    Explanations

    python def check_win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rebus
    0.46
    休闲
    0.42
     colourful
    0.41
     kanamycin
    0.41
    邻
    0.40
    ექს
    0.40
     thisTrial
    0.40
     robustness
    0.39
    trom
    0.38
    یی
    0.38
    POSITIVE LOGITS
     Nigam
    0.44
     Acosta
    0.42
    Attk
    0.38
     Players
    0.38
     athletes
    0.36
     board
    0.36
     Ashley
    0.36
     tossed
    0.36
     Shelby
    0.36
     Deniz
    0.36
    Act Density 0.008%

    No Known Activations