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

    Neuronpedia

    INDEX
    Explanations

    instances of bold formatting within the text

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

    HTML bold tag <b>

    np_acts-logits-general · gemini-2.0-flash

    break schedule and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </em>
    -0.62
    </strong>
    -0.53
    <em>
    -0.50
     
    -0.50
    ContextCompat
    -0.49
    tale
    -0.48
     Swamp
    -0.48
    Gatt
    -0.47
    ➟
    -0.47
    ٧
    -0.43
    POSITIVE LOGITS
    bibfield
    0.57
    ness
    0.57
    ly
    0.54
     enfans
    0.50
    addContainerGap
    0.50
    </b>
    0.50
    nya
    0.50
     endblock
    0.50
     aé
    0.48
    pośred
    0.48
    Act Density 0.189%

    No Known Activations