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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics and social issues

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

    before prepositions or adverbs

    np_acts-logits-general · gemini-2.0-flash

    phrasal verbs using nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNS
    -0.62
     оригіналу
    -0.57
    dominal
    -0.55
    HStack
    -0.54
    ITHUB
    -0.54
    ronic
    -0.53
     Kept
    -0.52
    fromCharCode
    -0.52
    laise
    -0.52
    rzost
    -0.51
    POSITIVE LOGITS
     out
    0.97
     down
    0.96
     up
    0.95
     off
    0.90
     away
    0.80
     asunder
    0.77
     välja
    0.73
     forward
    0.71
    findpost
    0.67
     OFDb
    0.65
    Act Density 0.431%

    No Known Activations