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

    Neuronpedia

    INDEX
    Explanations

    sequences of consecutive underscores

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

    code or proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typelib
    -0.60
    ########.
    -0.59
    WithIOException
    -0.51
     gyhoeddwyd
    -0.49
    Ƚ
    -0.48
    AddTagHelper
    -0.47
    nologue
    -0.47
    PerformLayout
    -0.47
    RenderAtEndOf
    -0.45
    קישורים
    -0.44
    POSITIVE LOGITS
     geda
    0.45
     Gubernur
    0.44
     arvio
    0.43
    ?>"
    0.43
     {?>
    0.42
     razões
    0.42
    variables
    0.40
     Erwachsene
    0.39
     Spéc
    0.39
    țional
    0.39
    Act Density 0.017%

    No Known Activations