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

    Neuronpedia

    INDEX
    Explanations

    structural elements and data types within programming or API-related content

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

    instance, length, <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     velho
    -0.46
    feitura
    -0.41
    word
    -0.38
    face
    -0.38
    abortion
    -0.38
    pitch
    -0.38
     neur
    -0.38
    area
    -0.37
    Msk
    -0.37
    ramid
    -0.37
    POSITIVE LOGITS
    mybatisplus
    0.56
    TypedDataSet
    0.54
    ThroughAttribute
    0.49
    Datuak
    0.49
    principalTable
    0.48
    parsedMessage
    0.45
     dAtA
    0.45
    UnknownFieldSet
    0.45
    SharedCtor
    0.45
     gekomen
    0.44
    Act Density 0.325%

    No Known Activations