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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations involving variables

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

    Expressions with exponents and arithmetic

    np_acts-logits-general · gemini-2.0-flash

    algebraic variables and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.57
    nodoc
    -0.50
    لينكات
    -0.50
    nestjs
    -0.48
     &___
    -0.45
    conscious
    -0.44
    ulman
    -0.42
    VIAF
    -0.42
    ंदीखरीदारी
    -0.41
    Chham
    -0.41
    POSITIVE LOGITS
    Third
    0.55
    THIRD
    0.52
     third
    0.51
    第三
    0.50
     Third
    0.50
     üçün
    0.47
    三人
    0.47
    ⓷
    0.47
    third
    0.47
    RotationOrder
    0.46
    Act Density 4.050%

    No Known Activations