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

    Neuronpedia

    INDEX
    Explanations

    punctuation and the structure of written text

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

    proper nouns after and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.49
    ArgsConstructor
    -0.47
    OGND
    -0.42
    MutableLiveData
    -0.39
    KEYCODE
    -0.39
    のですか
    -0.38
    woke
    -0.37
    parsedMessage
    -0.36
     թվական
    -0.35
    Насе
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.42
    новниш
    0.42
    nościo
    0.41
     vieill
    0.41
     Sauer
    0.41
     caucho
    0.40
    arraycopy
    0.40
     póster
    0.40
     memu
    0.39
    LEGGI
    0.39
    Act Density 0.740%

    No Known Activations