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

    Neuronpedia

    INDEX
    Explanations

    expressing hope and apology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desktops
    0.40
     alleles
    0.39
     pigments
    0.39
     এমনকি
    0.38
     organelles
    0.38
     stylesheets
    0.38
     artery
    0.38
     fingerprints
    0.38
     vacuoles
    0.37
     apertures
    0.37
    POSITIVE LOGITS
     Hopefully
    0.47
     hopefully
    0.44
     надеюсь
    0.43
    富有
    0.41
     मैं
    0.40
     weiteren
    0.39
    hopefully
    0.38
    sono
    0.38
     🙏
    0.38
     Semoga
    0.38
    Act Density 0.131%

    No Known Activations