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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

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

    Fractions and simple arithmetic

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols in math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.73
     <=",
    -0.52
    दी
    -0.48
     Uniti
    -0.47
    UnitTesting
    -0.46
    hamcrest
    -0.46
     Barley
    -0.45
     Ips
    -0.45
     uLocal
    -0.45
     rocha
    -0.44
    POSITIVE LOGITS
    <?
    0.65
     MainAxisSize
    0.63
    
    0.59
    TypedDataSet
    0.57
    setDefault
    0.56
    AntiForgeryToken
    0.56
    6
    0.55
     eighteen
    0.53
    六
    0.53
     Six
    0.52
    Act Density 0.796%

    No Known Activations