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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    Parenthetical remarks and asides

    np_acts-logits-general · gemini-2.0-flash

    emoticons and colloquialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Commencez
    -0.60
     “[
    -0.59
    ANDOM
    -0.56
    ">//
    -0.56
     “…
    -0.55
    LÄ
    -0.54
    τιά
    -0.53
     Tenggara
    -0.53
    umbi
    -0.52
    ⋙
    -0.52
    POSITIVE LOGITS
     resourceCulture
    0.71
     propOrder
    0.69
     Pls
    0.65
    anyway
    0.64
    hope
    0.59
     élevées
    0.59
    Btw
    0.57
     szcze
    0.56
    regards
    0.56
     holomorphic
    0.56
    Act Density 0.269%

    No Known Activations