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

    Neuronpedia

    INDEX
    Explanations

    expressed questions and statements in a conversational or advisory context

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

    Follows "all" or "you"

    np_acts-logits-general · gemini-2.0-flash

    you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.47
     propOrder
    -0.42
    んですか
    -0.41
     autorytatywna
    -0.41
    WriteLiteral
    -0.40
    のですか
    -0.39
    sidemargin
    -0.39
     Normdatei
    -0.38
     disponibilités
    -0.38
    SequentialGroup
    -0.38
    POSITIVE LOGITS
     known
    1.41
     know
    1.31
    known
    1.24
     Known
    1.16
     knows
    1.14
    Known
    1.13
    know
    1.11
     KNOWN
    1.10
    Know
    1.08
     bekannt
    1.07
    Act Density 0.385%

    No Known Activations