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

    Neuronpedia

    INDEX
    Explanations

    transitional words and phrases that indicate reasoning or contradiction

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

    conjunctive adverbs ending clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dõi
    -0.47
    Aiheesta
    -0.40
     nahilalakip
    -0.40
    xy
    -0.40
    engaruhi
    -0.39
     Stre
    -0.38
     Spa
    -0.38
     jaz
    -0.38
    pto
    -0.37
     pron
    -0.37
    POSITIVE LOGITS
    tagext
    0.57
    uxxxx
    0.56
     unknownFields
    0.47
    UnusedPrivate
    0.44
     useAppContext
    0.44
     typelib
    0.43
    anneer
    0.40
     enfans
    0.40
     antem
    0.40
     entanto
    0.40
    Act Density 0.077%

    No Known Activations