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

    Neuronpedia

    INDEX
    Explanations

    Boolean values and conditional statements

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

    boolean logic values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.52
     navel
    -0.50
     Abbey
    -0.49
     Navarro
    -0.48
    sdf
    -0.46
    SFER
    -0.46
     Eden
    -0.45
     Kiki
    -0.45
    Sever
    -0.45
    yntaxException
    -0.45
    POSITIVE LOGITS
     FALSE
    1.57
    FALSE
    1.53
    TRUE
    1.52
     TRUE
    1.52
     BOOL
    0.63
     whilst
    0.60
     Whilst
    0.58
    BASEPATH
    0.57
    oolean
    0.56
     WHEREAS
    0.54
    Act Density 0.011%

    No Known Activations