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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methodologies and experimental setups

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

    a specific study or scientific method

    np_acts-logits-general · gemini-2.0-flash

    technical definitions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typelib
    -0.38
    CWE
    -0.35
     MMMM
    -0.33
    OGND
    -0.33
    RTEE
    -0.32
     mib
    -0.32
     мәкал
    -0.32
    Jereo
    -0.31
    JspWriter
    -0.31
    userAgent
    -0.31
    POSITIVE LOGITS
     tarko
    0.68
     للاسماء
    0.63
     sisält
    0.60
    RenderAtEndOf
    0.54
    occupe
    0.53
    izante
    0.52
    üyor
    0.52
     meliputi
    0.52
    TagHelper
    0.51
     tuot
    0.50
    Act Density 0.744%

    No Known Activations