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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgement in conversations

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

    Regarding DSLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.89
     lenker
    -0.75
    ✨:
    -0.74
    :✨
    -0.71
    -0.69
    SBATCH
    -0.62
    adaptiveStyles
    -0.62
     ſta
    -0.60
     referrerpolicy
    -0.58
     ſind
    -0.58
    POSITIVE LOGITS
    CloseOperation
    0.41
     Ad
    0.34
     Adkins
    0.33
    FormState
    0.31
     ​​
    0.30
     N
    0.29
    Ad
    0.28
    DeclareMath
    0.28
     st
    0.28
     S
    0.28
    Act Density 0.084%

    No Known Activations