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

    Neuronpedia

    INDEX
    Explanations

    indicators of conditional statements and specific references to individuals or groups

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

    according to phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.52
     initComponents
    -0.49
    twimg
    -0.48
    ChildScrollView
    -0.48
    LayoutConstraint
    -0.47
    Gön
    -0.47
    帖最后由
    -0.45
    gdx
    -0.45
    AntiForgeryToken
    -0.44
     للمعارف
    -0.43
    POSITIVE LOGITS
    :✨
    0.54
     autorytatywna
    0.52
    Personendaten
    0.50
    ientras
    0.46
     Monfieur
    0.44
     obicei
    0.44
     codzien
    0.43
    NameInMap
    0.43
    jenigen
    0.43
     democrática
    0.42
    Act Density 0.001%

    No Known Activations