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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or expressions of denial

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

    French negation marker pas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.54
     CreateTagHelper
    -0.49
    kjø
    -0.46
    DataAnnotations
    -0.43
    SourceChecksum
    -0.42
     textView
    -0.42
     aján
    -0.41
    ritzau
    -0.41
     âgé
    -0.41
    ainville
    -0.41
    POSITIVE LOGITS
     pas
    1.13
     not
    0.84
     Not
    0.73
    not
    0.71
    Not
    0.68
     NOT
    0.67
     nicht
    0.58
     Pas
    0.58
     Nicht
    0.58
    IsContent
    0.57
    Act Density 0.004%

    No Known Activations