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

    Neuronpedia

    INDEX
    Explanations

    expressions related to necessity or requirements

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

    when needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.73
    }}}{
    -0.51
    UserScript
    -0.47
     surla
    -0.46
    '])){
    -0.46
    ']))
    -0.44
    }))
    -0.43
     चीज़ों
    -0.43
    DrawerToggle
    -0.42
    grunns
    -0.42
    POSITIVE LOGITS
     appropriately
    0.54
     appropriate
    0.52
     accordingly
    0.50
    omitempty
    0.50
    こんな感じで
    0.48
    ModelSerializer
    0.47
    Appropriate
    0.46
     endwhile
    0.46
    不时
    0.46
     nhàng
    0.45
    Act Density 0.016%

    No Known Activations