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

    Neuronpedia

    INDEX
    Explanations

    expressions related to legal or financial obligations

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

    Follows certain prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    duck down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    neo
    -0.56
    Degree
    -0.54
     neo
    -0.54
     Beecher
    -0.53
    ceo
    -0.53
    UnitTesting
    -0.53
    fea
    -0.52
    PageRoute
    -0.52
    preloader
    -0.52
     bieber
    -0.52
    POSITIVE LOGITS
    CloseOperation
    0.63
     pronunciation
    0.56
    classnames
    0.54
     aloud
    0.53
    OPSIS
    0.53
     gunpowder
    0.51
    ⎣
    0.51
     ſmall
    0.51
    Personendaten
    0.51
     LUMI
    0.50
    Act Density 0.441%

    No Known Activations