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

    Neuronpedia

    INDEX
    Explanations

    numeric values and sequences in the text

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

    Formatting numbers with periods

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cup
    -0.70
    glass
    -0.64
     taza
    -0.60
     glass
    -0.59
     a
    -0.59
    杯
    -0.51
     насељу
    -0.51
    cup
    -0.49
     morning
    -0.48
    Domains
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    1.09
    новниш
    0.72
     disambiguazione
    0.72
    IUrlHelper
    0.71
    SharedCtor
    0.71
     transférez
    0.68
    DockStyle
    0.66
    windowFixed
    0.66
    InjectAttribute
    0.66
    Хьажоргаш
    0.65
    Act Density 0.263%

    No Known Activations