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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ITER
    -0.07
    _examples
    -0.06
     abbreviation
    -0.06
    )v
    -0.06
    )t
    -0.06
    zier
    -0.06
    ційні
    -0.06
     escalating
    -0.06
    Checked
    -0.06
     Nath
    -0.06
    POSITIVE LOGITS
    (changes
    0.07
     despre
    0.07
    esson
    0.06
     petty
    0.06
    еться
    0.06
     wy
    0.06
     formula
    0.06
    警
    0.06
     discounts
    0.06
    .slug
    0.06
    Act Density 0.075%

    No Known Activations