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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LocalDate
    -0.06
    Du
    -0.06
     Du
    -0.06
     pundits
    -0.06
     Angels
    -0.06
     overdose
    -0.06
    	count
    -0.06
     du
    -0.06
    іть
    -0.06
    aterno
    -0.06
    POSITIVE LOGITS
    .Series
    0.06
    pciones
    0.06
    liced
    0.06
    !(
    0.06
    らず
    0.06
    UMMY
    0.06
    .done
    0.06
    _,,
    0.06
    _MULT
    0.06
    itimate
    0.06
    Act Density 0.043%

    No Known Activations