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

    Neuronpedia

    INDEX
    Explanations

    or followed by alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.90
     jiné
    0.85
     أي
    0.78
    任何
    0.75
     რომელი
    0.75
    哪个
    0.75
    Any
    0.74
     bárm
    0.71
    哪里
    0.70
    Other
    0.70
    POSITIVE LOGITS
     we
    1.12
     they
    1.09
     it
    0.98
     everything
    0.97
     crucially
    0.84
     EVERYTHING
    0.83
     shockingly
    0.82
     there
    0.80
    everything
    0.78
     plenty
    0.78
    Act Density 0.034%

    No Known Activations