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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棹
    -0.08
     mbox
    -0.07
     Ley
    -0.07
     Doming
    -0.07
     Dynam
    -0.07
     Maced
    -0.07
     أبي
    -0.07
    风雨
    -0.07
     bif
    -0.07
     pharmac
    -0.07
    POSITIVE LOGITS
    .Scan
    0.07
     Alarm
    0.07
    .Frame
    0.07
    (up
    0.07
    （笑
    0.07
    wiście
    0.07
     PCA
    0.06
    ハード
    0.06
    RAM
    0.06
    erve
    0.06
    Act Density 0.002%

    No Known Activations