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

    Neuronpedia

    INDEX
    Explanations

    favorable outcomes, profitable trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     playerId
    0.73
     مسئلے
    0.72
    episode
    0.72
    unicode
    0.71
    scorer
    0.71
    you
    0.69
     episódio
    0.69
     puissiez
    0.68
    ⅼ
    0.67
    ISO
    0.67
    POSITIVE LOGITS
     favorable
    1.19
     конку
    1.09
     favourable
    1.03
     lucrative
    0.98
     trendy
    0.95
     profitable
    0.94
     similar
    0.91
     opposite
    0.90
     favorables
    0.90
     fashionable
    0.88
    Act Density 0.002%

    No Known Activations