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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their various forms in sentences

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

    Follows "is", "es", or "It"

    np_acts-logits-general · gemini-2.0-flash

    German and English conjunctions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.56
     المنا
    -0.49
    menea
    -0.48
     dass
    -0.48
    AnchorTagHelper
    -0.47
    enumi
    -0.46
    ypep
    -0.46
     MwSt
    -0.46
    λλα
    -0.45
     TextAppearance
    -0.45
    POSITIVE LOGITS
     also
    0.96
     already
    0.88
     meanwhile
    0.87
     usually
    0.87
     unfortunately
    0.86
     always
    0.85
     moreover
    0.80
     therefore
    0.79
     indeed
    0.78
     además
    0.77
    Act Density 0.076%

    No Known Activations