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

    Neuronpedia

    INDEX
    Explanations

    when, after, now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COLLECT
    0.24
     حروف
    0.21
     свето
    0.20
     острова
    0.20
     getY
    0.20
     EXECUTIVE
    0.20
     olefins
    0.20
     arrows
    0.20
    Arrows
    0.20
     imperatives
    0.19
    POSITIVE LOGITS
     Comp
    0.20
    den
    0.19
    uky
    0.18
     renamed
    0.18
    org
    0.18
    Comp
    0.18
    ibfk
    0.17
     Sabha
    0.17
    denom
    0.17
     Rename
    0.17
    Act Density 0.011%

    No Known Activations