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

    Neuronpedia

    INDEX
    Explanations

    punctuation that occurs at the end of sentences

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

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.98
     незавершена
    -0.84
    ReusableCell
    -0.78
    ágenes
    -0.74
    StoryboardSegue
    -0.74
    BufferException
    -0.72
    parsedMessage
    -0.71
     JpaRepository
    -0.69
     transfieras
    -0.69
    səhifə
    -0.69
    POSITIVE LOGITS
    <bos>
    0.52
    !
    0.46
     of
    0.40
    ting
    0.38
    <eos>
    0.37
     Of
    0.36
    ↵
    0.36
    $
    0.36
     &
    0.35
    st
    0.35
    Act Density 0.016%

    No Known Activations