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

    Neuronpedia

    INDEX
    Explanations

    patterns related to academic references and citations

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

    legal or numerical identifiers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by words or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    習
    -0.50
    ngdoc
    -0.50
     odkazy
    -0.48
     חיצוניים
    -0.47
    풍
    -0.46
    žní
    -0.45
     dân
    -0.45
    unknownFields
    -0.44
    appan
    -0.44
    LabelTagHelper
    -0.44
    POSITIVE LOGITS
    发表于
    0.60
    ualaikum
    0.57
    WriteTagHelper
    0.57
     bezeichneter
    0.56
    Gemeinden
    0.56
    Espèce
    0.54
     tarko
    0.54
    äher
    0.54
    orative
    0.53
     Protobuf
    0.53
    Act Density 0.122%

    No Known Activations