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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to scientific documents

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

    Tokens appearing before bracketed numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    references and data extractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.70
    liceerd
    -0.68
    DockStyle
    -0.61
    lysm
    -0.60
    Empereur
    -0.57
     المعيارى
    -0.54
    出版年
    -0.54
    rungsseite
    -0.52
    ponses
    -0.52
     собі
    -0.51
    POSITIVE LOGITS
    BufferException
    0.37
     defaultstate
    0.35
    WithIOException
    0.34
    Page
    0.32
    收
    0.31
     betweenstory
    0.31
     bes
    0.31
    page
    0.31
     muka
    0.30
    ListPage
    0.30
    Act Density 0.506%

    No Known Activations