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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marian
    -0.07
    arian
    -0.06
     Fur
    -0.06
    _models
    -0.06
     lun
    -0.06
    arios
    -0.06
    =my
    -0.06
    似
    -0.06
    ыш
    -0.06
    birds
    -0.06
    POSITIVE LOGITS
     lign
    0.07
    RODUCTION
    0.07
    <p
    0.07
    [I
    0.07
     놓
    0.07
    γωγ
    0.06
    .writerow
    0.06
    &ZeroWidthSpace
    0.06
    Sy
    0.06
    RO
    0.06
    Act Density 0.000%

    No Known Activations