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

    Neuronpedia

    INDEX
    Explanations

    sudden realization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trafi
    0.78
     ostensibly
    0.74
     nominally
    0.74
    තාව
    0.73
     relentlessly
    0.69
     reportedly
    0.69
     Initially
    0.68
    acaks
    0.68
    竟然
    0.68
    僅
    0.68
    POSITIVE LOGITS
     realize
    2.37
     realizing
    2.20
     realized
    2.19
     realization
    2.11
     realizes
    2.02
     realising
    1.90
     realised
    1.89
     realisation
    1.86
     realise
    1.82
     realizations
    1.74
    Act Density 0.030%

    No Known Activations