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

    Neuronpedia

    INDEX
    Explanations

    patterns in numerical values related to calculations or mathematical expressions

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

    numbers and division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bordir
    -0.54
     réfugiés
    -0.54
     zelve
    -0.53
     dezelve
    -0.53
    contentLoaded
    -0.51
     Ausnahme
    -0.50
     colectiva
    -0.50
     aanwezig
    -0.48
    retudo
    -0.47
     zoude
    -0.47
    POSITIVE LOGITS
    ChildScrollView
    0.69
     $/
    0.60
     المعيارى
    0.58
    `/
    0.57
    $/
    0.57
    ?/
    0.56
     /
    0.55
    €/
    0.54
    /</
    0.54
    |/
    0.53
    Act Density 0.068%

    No Known Activations