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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and symbols

    oai_token-act-pair · gemini-2.0-flash

    dot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.78
     <=",
    -0.73
     ©️
    -0.68
    ±
    -0.67
     betweenstory
    -0.66
     estekak
    -0.60
     defStyleAttr
    -0.59
     '\\;'
    -0.58
     Tiberius
    -0.57
    Senegal
    -0.56
    POSITIVE LOGITS
    }{*}{
    0.73
     оригіналу
    0.65
    multicolumn
    0.61
     rowspan
    0.59
     the
    0.59
    těte
    0.59
    \{\\
    0.58
     middle
    0.57
    Mediabestanden
    0.57
     mid
    0.56
    Act Density 1.566%

    No Known Activations