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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kerry
    -0.07
    Cop
    -0.07
     Bai
    -0.07
     Field
    -0.07
     Lowell
    -0.06
    _multiple
    -0.06
     Hockey
    -0.06
     Variety
    -0.06
     Bass
    -0.06
    _List
    -0.06
    POSITIVE LOGITS
    Interval
    0.07
    адж
    0.06
     آلة
    0.06
    정이
    0.06
    engin
    0.06
    mani
    0.06
     asks
    0.06
    ５
    0.06
    Em
    0.06
    realloc
    0.06
    Act Density 0.177%

    No Known Activations