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

    Neuronpedia

    INDEX
    Explanations

    content that discusses mental health strategies and self-improvement

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

    explains contents of books or guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.57
    parsedMessage
    -0.51
    SourceChecksum
    -0.48
    ConstraintMaker
    -0.48
    ̈́
    -0.48
     дописавши
    -0.45
     referrerpolicy
    -0.45
    andExpect
    -0.45
    SerializedSize
    -0.45
     Appreciation
    -0.45
    POSITIVE LOGITS
     book
    0.52
     chapters
    0.49
     guide
    0.46
     practical
    0.44
    newtheorem
    0.42
     prácti
    0.40
     author
    0.40
     chapter
    0.36
     authors
    0.36
     memoir
    0.36
    Act Density 0.031%

    No Known Activations