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

    Neuronpedia

    INDEX
    Explanations

    the best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اولا
    0.81
     സമൂ
    0.80
     আন্তরিক
    0.73
    Unless
    0.73
    গ্রস্থ
    0.71
    shows
    0.70
    ോഗ
    0.66
    statements
    0.66
    enas
    0.66
     vonat
    0.65
    POSITIVE LOGITS
     perfect
    1.32
     Perfect
    1.30
     ideal
    1.12
     idéale
    1.12
     идеа
    1.11
    Perfect
    1.09
     ideale
    1.03
     idéal
    1.02
    perfect
    1.02
     PERFECT
    1.01
    Act Density 0.203%

    No Known Activations