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

    Neuronpedia

    INDEX
    Explanations

    moment of realization or discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सीएल
    0.42
     mín
    0.40
     claimed
    0.38
     Outcomes
    0.38
     trouvent
    0.37
     skú
    0.36
    িপি
    0.36
    U
    0.36
     indicó
    0.36
    仍然
    0.35
    POSITIVE LOGITS
     realise
    0.64
     realize
    0.63
     bahwa
    0.62
     realizes
    0.55
     realization
    0.51
     realises
    0.50
     that
    0.49
     truths
    0.49
     bahawa
    0.48
     realized
    0.48
    Act Density 0.009%

    No Known Activations