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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formatted data structures

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

    Mathematical or scientific notation including zeros

    np_acts-logits-general · gemini-2.0-flash

    N.A. or neither

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.57
     nonUne
    -0.55
    :✨
    -0.55
     enfans
    -0.54
    ✨:
    -0.54
    __*/
    -0.52
    MessageOf
    -0.52
     GenerationType
    -0.52
    AndroidJUnit
    -0.52
    IndentedString
    -0.51
    POSITIVE LOGITS
     uLocal
    0.54
     neither
    0.38
    astéroïdes
    0.38
    sighs
    0.37
     Neither
    0.36
    stat
    0.35
     חיצוניים
    0.34
    Neither
    0.33
    neither
    0.32
    льзя
    0.31
    Act Density 0.491%

    No Known Activations