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

    Neuronpedia

    INDEX
    Explanations

    say ":"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Levels
    -0.07
    ges
    -0.06
     datasets
    -0.06
    bam
    -0.06
     Xavier
    -0.06
    agnostics
    -0.06
    アー
    -0.06
    Dto
    -0.06
    accum
    -0.06
    ابع
    -0.06
    POSITIVE LOGITS
    べて
    0.07
     freelance
    0.06
    ily
    0.06
    (inplace
    0.06
     Lumia
    0.06
     improvised
    0.06
    .newBuilder
    0.06
    toPromise
    0.06
     شده
    0.06
     delicate
    0.06
    Act Density 0.004%

    No Known Activations