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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

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

    Following "not" or negations

    np_acts-logits-general · gemini-2.0-flash

    not followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hsl
    -0.35
    Thursday
    -0.34
    The
    -0.34
     atitude
    -0.33
    SPI
    -0.33
     Trä
    -0.32
    lastung
    -0.32
     envie
    -0.32
    Wednesday
    -0.31
     precau
    -0.31
    POSITIVE LOGITS
     blevet
    0.91
     blitt
    0.79
    CppMethod
    0.79
     nakalista
    0.76
    IsContent
    0.73
    enablog
    0.71
    __*/
    0.68
     EconPapers
    0.68
     queſta
    0.68
    <unused41>
    0.67
    Act Density 0.272%

    No Known Activations