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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ספר
    0.66
     ਗ
    0.66
     salário
    0.66
    Intercept
    0.65
     দাঁড়িয়ে
    0.64
     फ्लिप
    0.64
     derived
    0.64
    derived
    0.63
     воро
    0.63
     सीजन
    0.62
    POSITIVE LOGITS
     bracket
    1.31
    bracket
    1.27
     Bracket
    1.25
    Bracket
    1.15
     brackets
    1.10
    brackets
    1.03
     Tournament
    0.99
     tournament
    0.99
     torneo
    0.80
    tournament
    0.78
    Act Density 0.065%

    No Known Activations