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

    Neuronpedia

    INDEX
    Explanations

    code with time delays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .WRAP
    -0.07
    ouple
    -0.07
    同学
    -0.07
     눈을
    -0.06
     zů
    -0.06
    份
    -0.06
     약
    -0.06
    >You
    -0.06
    수로
    -0.06
     خلال
    -0.06
    POSITIVE LOGITS
    _hdr
    0.06
    (nome
    0.06
    _lista
    0.06
    contents
    0.06
     ==(
    0.06
    ρες
    0.06
    equals
    0.06
    _precision
    0.06
    Lista
    0.06
    _timing
    0.06
    Act Density 0.006%

    No Known Activations