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

    Neuronpedia

    INDEX
    Explanations

    concepts related to understanding and interpretation

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

    in that sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.56
    :✨
    -0.45
     démocr
    -0.44
     mergeFrom
    -0.43
     ninguno
    -0.42
    HasIndex
    -0.42
     asesino
    -0.42
     goederen
    -0.41
     gruesa
    -0.41
    出版年
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.54
    FTFY
    0.48
    Rüyada
    0.44
    ❦
    0.43
    兼
    0.42
    endphp
    0.42
    denn
    0.41
    latego
    0.40
     PUN
    0.40
    PostInfinity
    0.40
    Act Density 0.759%

    No Known Activations