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

    Neuronpedia

    INDEX
    Explanations

    contributions related to scientific calculations and modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "contribution" or "contributions"

    np_acts-logits-general · gemini-2.0-flash

    contribution of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Breach
    -0.38
     вжи
    -0.36
    oredCriteria
    -0.36
     select
    -0.34
     noDo
    -0.33
     Crash
    -0.33
    kiet
    -0.32
    select
    -0.32
     proté
    -0.31
     pinulongan
    -0.31
    POSITIVE LOGITS
     contribution
    1.52
     contributions
    1.45
    contribution
    1.28
     Contribution
    1.27
    Contribution
    1.23
     Contributions
    1.23
    contributions
    1.19
    Contributions
    1.17
     contribución
    1.16
     CONTRIBUTION
    1.15
    Act Density 1.545%

    No Known Activations