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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of denial

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

    negation and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.60
    RenderAtEndOf
    -0.56
     endwhile
    -0.52
     okuyayım
    -0.51
    ivka
    -0.49
     vVar
    -0.47
    ValueStyle
    -0.47
    NewUrlParser
    -0.47
    󠁢
    -0.47
    AISSEE
    -0.46
    POSITIVE LOGITS
     not
    0.85
    Não
    0.75
     Not
    0.75
    Tidak
    0.73
     cannot
    0.69
     ולא
    0.69
     Não
    0.69
    Not
    0.68
    Không
    0.66
     tidak
    0.66
    Act Density 0.003%

    No Known Activations