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

    Neuronpedia

    INDEX
    Explanations

    statements of necessity or obligation

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

    must say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.67
     resourceCulture
    -0.62
    rungsseite
    -0.61
    省市镇
    -0.61
    PreferredItem
    -0.59
    TagMode
    -0.57
    empêcher
    -0.57
    ragalactic
    -0.56
     Савезне
    -0.52
    chemise
    -0.52
    POSITIVE LOGITS
    nlm
    0.32
     ими
    0.29
    []}
    0.29
    Lø
    0.29
     ethics
    0.29
    djangoproject
    0.28
     stretch
    0.28
     sprintf
    0.28
     wing
    0.27
    stretch
    0.27
    Act Density 0.000%

    No Known Activations