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

    Neuronpedia

    INDEX
    Explanations

    phrases or sections with a strong emphasis on definitive or absolute statements

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

    proper nouns and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.40
     dụ
    -0.40
    cassert
    -0.40
    ://"
    -0.39
    AssignableFrom
    -0.38
    LocationManager
    -0.38
    </i>
    -0.38
    ッケージ
    -0.37
     tearDown
    -0.37
    </thead>
    -0.36
    POSITIVE LOGITS
    expandindo
    0.71
    :✨
    0.70
     للاسماء
    0.57
    \{\\
    0.57
    InjectAttribute
    0.53
    labus
    0.51
     surla
    0.51
     autorytatywna
    0.50
    Cyfarwyddwr
    0.50
    :][
    0.49
    Act Density 0.081%

    No Known Activations