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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to programming and data processing

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

    Subtraction or values after subtraction words

    np_acts-logits-general · gemini-2.0-flash

    difference or subtraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.53
    <?
    -0.50
    writeField
    -0.50
     EClass
    -0.47
     gainera
    -0.46
    verifyException
    -0.45
    ReusableCell
    -0.45
    queryInterface
    -0.45
     дода
    -0.44
    يميديا
    -0.43
    POSITIVE LOGITS
    subtract
    0.85
     minus
    0.84
     subtract
    0.81
     subtracting
    0.79
     −
    0.76
     }}-
    0.72
     Minus
    0.70
    减
    0.68
    Minus
    0.67
     Subtract
    0.67
    Act Density 0.718%

    No Known Activations