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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating gradual or unexpected changes and processes

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

    manner or extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.54
    hyrchwyd
    -0.53
    zbęd
    -0.48
    alakip
    -0.48
    fillType
    -0.48
     дописавши
    -0.47
     snippetHide
    -0.47
    Jereo
    -0.45
    RenderAtEndOf
    -0.44
     connais
    -0.44
    POSITIVE LOGITS
    有意
    0.49
     actively
    0.48
     passively
    0.44
    actively
    0.43
     <<<<<<<<<<<<<<
    0.42
    あえて
    0.42
     temporarily
    0.41
     further
    0.41
    故意
    0.41
    不时
    0.41
    Act Density 0.014%

    No Known Activations