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

    Neuronpedia

    INDEX
    Explanations

    expressions related to authenticity and opinions

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

    Colloquial smile emoticons

    np_acts-logits-general · gemini-2.0-flash

    laughter and emoticons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.66
    AndEndTag
    -0.65
    tagHelperRunner
    -0.63
    脚注の使い方
    -0.60
     snippetHide
    -0.58
     للمعارف
    -0.58
     referenties
    -0.54
    -0.54
     فريبيس
    -0.53
     يتيمه
    -0.53
    POSITIVE LOGITS
    :)
    0.44
    😊
    0.40
    :(
    0.39
     LOL
    0.38
     :))
    0.38
    ^^
    0.37
    isielt
    0.36
    뀜
    0.36
     cascada
    0.36
     :)
    0.35
    Act Density 0.203%

    No Known Activations