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

    Neuronpedia

    INDEX
    Explanations

    occurrences of articles and definite determiners

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

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.70
    KommentareTeilen
    -0.61
    ագրություններ
    -0.60
     Normdatei
    -0.58
    OGND
    -0.58
    Datuak
    -0.57
    UnknownFields
    -0.56
     awakeFromNib
    -0.56
     kasarigan
    -0.56
    AccessorTable
    -0.54
    POSITIVE LOGITS
     denna
    0.46
     this
    0.46
    This
    0.43
    この
    0.43
     данном
    0.39
    这个
    0.38
     This
    0.38
     proposal
    0.37
     questa
    0.36
     cette
    0.35
    Act Density 0.116%

    No Known Activations