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

    Neuronpedia

    INDEX
    Explanations

    the word "do" and its variations

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

    "Do" followed by a negative or modal verb

    np_acts-logits-general · gemini-2.0-flash

    auxiliary "do" or "does"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.82
    CloseOperation
    -0.77
    ImageContext
    -0.68
    antMatchers
    -0.68
    IUrlHelper
    -0.68
     decorativa
    -0.65
     soient
    -0.65
    ViewImports
    -0.64
     redenen
    -0.64
    WriteTagHelper
    -0.64
    POSITIVE LOGITS
     not
    1.12
     have
    1.10
     indeed
    1.09
     seem
    1.02
     NOT
    0.96
     appear
    0.90
     require
    0.86
     exist
    0.85
     contain
    0.85
     happen
    0.84
    Act Density 0.098%

    No Known Activations