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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eming
    -0.07
     Books
    -0.07
    \base
    -0.07
     CEOs
    -0.07
    _ng
    -0.06
    _min
    -0.06
    .refs
    -0.06
    .getChild
    -0.06
     Chúng
    -0.06
    ARK
    -0.06
    POSITIVE LOGITS
     Warranty
    0.06
     governo
    0.06
    気に入
    0.06
    0.05
     moderator
    0.05
     souvenir
    0.05
    รอบ
    0.05
    หาย
    0.05
     scen
    0.05
     divisible
    0.05
    Act Density 0.010%

    No Known Activations