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

    Neuronpedia

    INDEX
    Explanations

    references to academic studies and researchers

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

    many researchers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.58
     GenerationType
    -0.56
    CPtr
    -0.54
     ujednoznacz
    -0.53
    awtextra
    -0.52
    TextInputLayout
    -0.52
     հղումներ
    -0.49
    RenderAtEndOf
    -0.49
    keyColumn
    -0.48
    hint
    -0.47
    POSITIVE LOGITS
     many
    1.16
     Many
    1.11
    Many
    1.08
    many
    0.97
     Muchos
    0.96
     MANY
    0.95
    MANY
    0.90
    许多
    0.88
     muchos
    0.87
     viele
    0.86
    Act Density 0.231%

    No Known Activations