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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    роиз
    -0.08
    689
    -0.07
    Numer
    -0.07
    _ATOM
    -0.06
    .decor
    -0.06
    anzi
    -0.06
    .getInt
    -0.06
    India
    -0.06
    _AMOUNT
    -0.06
    код
    -0.06
    POSITIVE LOGITS
    zung
    0.06
    encil
    0.06
     widespread
    0.06
     ratings
    0.06
     puzzles
    0.06
     |>
    0.06
     grading
    0.06
    ublished
    0.06
     accomplishments
    0.06
     王
    0.06
    Act Density 0.064%

    No Known Activations