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

    Neuronpedia

    INDEX
    Explanations

    things that seem or look

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Apparently
    0.71
     Apparently
    0.67
     apparently
    0.65
     apparent
    0.63
     aparentemente
    0.61
    apparent
    0.58
    apparently
    0.57
    明らかに
    0.53
     supposedly
    0.51
     कथित
    0.49
    POSITIVE LOGITS
     sem
    0.74
     SEM
    0.73
     Sem
    0.72
     seem
    0.71
    Sem
    0.70
    sem
    0.69
    SEM
    0.66
     seems
    0.63
     look
    0.63
     SE
    0.58
    Act Density 0.052%

    No Known Activations