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

    Neuronpedia

    INDEX
    Explanations

    smooth and rough descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    regation
    0.46
    watchlist
    0.45
    地震
    0.43
    statistic
    0.42
     জনসং
    0.42
    oomla
    0.42
     wollten
    0.41
     الجمهور
    0.41
    rtel
    0.41
     INSEE
    0.41
    POSITIVE LOGITS
     orb
    0.58
     NPS
    0.53
     Orb
    0.50
    -
    0.50
     nl
    0.49
     Hawaii
    0.45
     MIF
    0.45
     org
    0.45
     wire
    0.45
    L
    0.45
    Act Density 0.001%

    No Known Activations