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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TH
    -0.06
    손
    -0.06
    nP
    -0.06
    District
    -0.06
    Ant
    -0.06
     osobní
    -0.06
    .sub
    -0.06
     kháng
    -0.06
     fabs
    -0.06
    	Date
    -0.06
    POSITIVE LOGITS
    ymbols
    0.07
     aberr
    0.07
    rats
    0.07
    #{
    0.07
     powers
    0.07
     '%
    0.07
     Comprehensive
    0.06
    ตร
    0.06
    HT
    0.06
     gross
    0.06
    Act Density 0.017%

    No Known Activations