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

    Neuronpedia

    INDEX
    Explanations

    references to attention and its related concepts

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

    apple and its products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.52
    ReusableCell
    -0.48
    VIAF
    -0.48
    ModelForm
    -0.45
     dévelo
    -0.43
    gründet
    -0.43
    Rüyada
    -0.42
     Publicar
    -0.41
    StructEnd
    -0.41
     sèche
    -0.40
    POSITIVE LOGITS
     Attention
    1.86
    Attention
    1.86
     attention
    1.75
    attention
    1.63
     ATTENTION
    1.55
    ATTENTION
    1.45
    Attn
    1.24
     attentions
    1.24
     atención
    1.19
    ATTN
    1.15
    Act Density 0.013%

    No Known Activations