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

    Neuronpedia

    INDEX
    Explanations

    company acquisitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ExpectedConditions
    -0.08
     הבע
    -0.07
    .shtml
    -0.07
    蛎
    -0.07
    ismo
    -0.07
    _validator
    -0.07
     Xxx
    -0.07
    私营
    -0.07
    ('?
    -0.06
    unei
    -0.06
    POSITIVE LOGITS
    phone
    0.07
    fac
    0.07
    BOARD
    0.07
    dit
    0.07
    _eth
    0.06
    "/
    0.06
    tol
    0.06
    serial
    0.06
    /table
    0.06
    戴着
    0.06
    Act Density 0.041%

    No Known Activations