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

    Neuronpedia

    INDEX
    Explanations

    terms related to data or information within a technical context

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

    data structures and programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.74
     atracción
    -0.52
     reputación
    -0.51
     plegable
    -0.50
     certificación
    -0.49
     inauguración
    -0.45
     renovación
    -0.45
     atraer
    -0.45
     cremallera
    -0.45
     rodilla
    -0.44
    POSITIVE LOGITS
     data
    1.84
     Data
    1.63
    data
    1.48
     DATA
    1.47
    Data
    1.45
    DATA
    1.34
    数据
    1.28
    データ
    1.23
     getData
    1.23
     datas
    1.21
    Act Density 0.073%

    No Known Activations