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

    Neuronpedia

    INDEX
    Explanations

    tax rates and thresholds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bor
    0.39
    Monthly
    0.39
    ii
    0.38
    றை
    0.38
     pont
    0.38
    iteta
    0.37
     streamed
    0.37
    rout
    0.36
    ээ
    0.36
     খরচ
    0.36
    POSITIVE LOGITS
     cigars
    0.44
    SMB
    0.43
     wax
    0.40
    水を
    0.40
     cigar
    0.38
     décrire
    0.38
     Candles
    0.36
     Reun
    0.36
    蠟
    0.36
     parejas
    0.36
    Act Density 0.002%

    No Known Activations