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

    Neuronpedia

    INDEX
    Explanations

    SATA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吴
    -0.08
    uire
    -0.07
    。当
    -0.07
    guild
    -0.07
     phases
    -0.06
     кан
    -0.06
    ，当
    -0.06
    och
    -0.06
    _TEAM
    -0.06
    准备
    -0.06
    POSITIVE LOGITS
     SATA
    0.12
    ata
    0.08
    commit
    0.07
    fa
    0.07
     poisoned
    0.06
     önlem
    0.06
     Surre
    0.06
    ="↵
    0.06
     Soup
    0.06
     Haw
    0.06
    Act Density 0.001%

    No Known Activations