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

    Neuronpedia

    INDEX
    Explanations

    negative constructs and expressions of inability

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

    Follows negative words: "not," "never"

    np_acts-logits-general · gemini-2.0-flash

    negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    drawSprites
    -0.66
    handedly
    -0.55
    lata
    -0.52
    tileno
    -0.50
    Bae
    -0.50
    ory
    -0.50
     Jury
    -0.49
     treo
    -0.49
    kian
    -0.49
     ControllerBase
    -0.49
    POSITIVE LOGITS
     pesante
    0.55
    twimg
    0.52
     ModelExpression
    0.51
    berday
    0.49
     /\.(
    0.48
     تضيفلها
    0.47
    Dichloropropane
    0.46
     varmt
    0.46
    ⁷
    0.46
     lacking
    0.46
    Act Density 0.023%

    No Known Activations