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

    Neuronpedia

    INDEX
    Explanations

    win potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stretcher
    0.43
    当て
    0.37
    当
    0.37
    文艺
    0.36
    粮食
    0.36
     Tsing
    0.35
    রোগ
    0.35
     অংশ
    0.35
     chai
    0.35
    LensFlare
    0.35
    POSITIVE LOGITS
    Casino
    0.51
     pokies
    0.49
     Casinos
    0.47
     Pok
    0.46
     Casino
    0.46
     casino
    0.45
    Pok
    0.44
     Au
    0.42
    proved
    0.40
     casinos
    0.39
    Act Density 0.000%

    No Known Activations