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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or doubt in decision-making contexts

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

    affirmative responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alumínio
    -0.39
     față
    -0.36
     löytyy
    -0.36
     berbasis
    -0.35
     condição
    -0.34
     unterschiedlich
    -0.34
    sträger
    -0.34
     projetos
    -0.34
     vermelha
    -0.34
    ViewFeatures
    -0.34
    POSITIVE LOGITS
    IsContent
    0.62
    WriteTagHelper
    0.61
     nonUne
    0.60
    رشف
    0.59
    abetes
    0.55
     actionBar
    0.53
    ConstraintMaker
    0.53
    SequentialGroup
    0.52
     CreateTagHelper
    0.52
     aDecoder
    0.52
    Act Density 0.200%

    No Known Activations