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

    Neuronpedia

    INDEX
    Explanations

    numerical values and related command instructions

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

    "0x" followed by a hexadecimal digit

    np_acts-logits-general · gemini-2.0-flash

    quarter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.56
    Autoritní
    -0.50
    divarius
    -0.49
    hore
    -0.49
     trồng
    -0.47
     kling
    -0.47
    stö
    -0.46
    ifer
    -0.45
     glatt
    -0.44
    urgy
    -0.44
    POSITIVE LOGITS
     quarter
    0.72
     quartered
    0.69
    quarter
    0.68
     QUARTER
    0.67
     quarters
    0.65
    Quarter
    0.61
     Quarters
    0.61
     Quarter
    0.61
     Мексичка
    0.58
     ModelExpression
    0.58
    Act Density 1.144%

    No Known Activations