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

    Neuronpedia

    INDEX
    Explanations

    specific formatting elements in code or style sheets

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.64
     desmotivaciones
    -0.63
     transférez
    -0.62
     complètes
    -0.60
     miniaturka
    -0.55
     oldValue
    -0.54
     Constitucional
    -0.54
     müſſen
    -0.53
     complète
    -0.52
     démocr
    -0.52
    POSITIVE LOGITS
    makeConstraints
    0.55
    HasAnnotation
    0.51
    IntoConstraints
    0.47
    stylesheet
    0.43
     InputDecoration
    0.39
    様
    0.38
    cult
    0.36
    ConstraintMaker
    0.35
    css
    0.35
    gwt
    0.34
    Act Density 0.004%

    No Known Activations