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

    Neuronpedia

    INDEX
    Explanations

    list of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     झाल्यावर
    0.35
     Schönheit
    0.34
    imizu
    0.34
     проблема
    0.33
    Improving
    0.33
     जलन
    0.33
     бола
    0.33
     औ
    0.33
     ఆ
    0.33
     നല്‍ക
    0.33
    POSITIVE LOGITS
     years
    0.43
     dollars
    0.38
     digits
    0.37
     dollar
    0.35
     pages
    0.35
     casos
    0.34
     rows
    0.33
     factories
    0.33
     keyboards
    0.33
     sectors
    0.33
    Act Density 0.017%

    No Known Activations