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

    Neuronpedia

    INDEX
    Explanations

    concepts related to equality and fair treatment

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

    equal, equality, equally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.56
    charCode
    -0.48
    CardHeader
    -0.46
     Roskov
    -0.45
    ernalia
    -0.45
    avigation
    -0.43
    cleo
    -0.42
    cstdio
    -0.42
     magasiner
    -0.41
    ArgumentParser
    -0.41
    POSITIVE LOGITS
     equal
    1.36
    equal
    1.27
    Equal
    1.27
     equality
    1.23
     Equal
    1.21
     EQUAL
    1.21
    EQUAL
    1.20
     égal
    1.16
     Equality
    1.10
    equality
    1.06
    Act Density 0.059%

    No Known Activations