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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ton
    -0.07
    annie
    -0.07
    Record
    -0.07
    ्वप
    -0.06
    ugu
    -0.06
    998
    -0.06
    header
    -0.06
    "d
    -0.06
    _Frame
    -0.06
     render
    -0.06
    POSITIVE LOGITS
    過
    0.07
    _overflow
    0.07
    有
    0.06
    社會
    0.06
     Returns
    0.06
    مول
    0.06
    并
    0.06
     لع
    0.06
     entreprise
    0.06
     건강
    0.06
    Act Density 0.005%

    No Known Activations