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

    Neuronpedia

    INDEX
    Explanations

    noticing unusual or surprising things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unfortunately
    0.62
     malheureusement
    0.61
    Unfortunately
    0.57
    heureusement
    0.54
     Unfortunately
    0.54
    unfortunately
    0.53
     aufgrund
    0.50
     fortunately
    0.49
    Sadly
    0.49
     दुर्भाग्य
    0.48
    POSITIVE LOGITS
    明明
    0.73
     seem
    0.70
     seemingly
    0.67
    seem
    0.66
     none
    0.64
     почти
    0.64
     semblent
    0.63
     Neither
    0.63
     despite
    0.61
    好像
    0.61
    Act Density 0.006%

    No Known Activations