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

    Neuronpedia

    INDEX
    Explanations

    sports scores and wins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bakter
    0.41
     pathogenic
    0.41
     perlu
    0.41
    <unused956>
    0.39
    既存
    0.37
     lapisan
    0.37
     juniper
    0.37
     benutzer
    0.36
     ancho
    0.36
    Ⲱ
    0.36
    POSITIVE LOGITS
     victories
    0.50
     totals
    0.48
     scoreless
    0.47
     impressively
    0.47
     scored
    0.46
     scoring
    0.46
    scored
    0.45
     tally
    0.44
     consecutive
    0.44
     नाबाद
    0.44
    Act Density 0.033%

    No Known Activations