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

    Neuronpedia

    INDEX
    Explanations

    references to the abbreviation "DON" in various contexts

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

    don and dont variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.51
    BindingResult
    -0.51
    MessageTagHelper
    -0.51
    FunctionFlags
    -0.48
    bleau
    -0.48
    utilisons
    -0.47
    -------
    -0.47
    новништво
    -0.47
    awtextra
    -0.47
    belea
    -0.46
    POSITIVE LOGITS
    DON
    0.89
     DON
    0.73
    ValueStyle
    0.43
    DONT
    0.43
     DONT
    0.40
    DO
    0.40
    Especificación
    0.40
    Donnie
    0.40
    Zar
    0.40
    Golden
    0.40
    Act Density 0.003%

    No Known Activations