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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

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

    Numbers in subtitles

    np_acts-logits-general · gemini-2.0-flash

    numbers and timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idin
    -0.48
     Roswell
    -0.48
     Eddie
    -0.46
    europa
    -0.45
     Tato
    -0.45
     Tata
    -0.45
     Patro
    -0.45
    OutputType
    -0.44
    efec
    -0.44
     johnny
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.77
    +#+
    0.61
    gridad
    0.58
     iniquity
    0.57
    gonic
    0.57
    awaiter
    0.57
     lundi
    0.56
     الرخصة
    0.56
    الحياه
    0.55
     connexes
    0.55
    Act Density 0.417%

    No Known Activations