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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筑
    -0.06
     increments
    -0.06
     پزشکی
    -0.06
     agreements
    -0.06
    _MB
    -0.06
     Zodiac
    -0.06
     Attention
    -0.06
     Billing
    -0.06
    (builder
    -0.06
     يست
    -0.06
    POSITIVE LOGITS
    [char
    0.07
    ¡
    0.06
    abcdefghijkl
    0.06
    apel
    0.06
     schw
    0.06
     meme
    0.06
    =start
    0.06
    -saving
    0.06
     TERMIN
    0.06
    return
    0.06
    Act Density 0.003%

    No Known Activations