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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and."

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

    Immediately follows the word "And" or "and"

    np_acts-logits-general · gemini-2.0-flash

    conjunction preceding names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.75
    SuspendLayout
    -0.60
    UnsafeEnabled
    -0.59
    دانشنامهٔ
    -0.59
    SequentialGroup
    -0.59
     incluso
    -0.58
    呼ば
    -0.57
    __':
    -0.54
    一緒に
    -0.54
    共に
    -0.54
    POSITIVE LOGITS
     Réponses
    0.59
     CreateTagHelper
    0.57
     quot
    0.56
    AccessorTable
    0.56
    lt
    0.53
     zwar
    0.53
    gt
    0.51
    Personendaten
    0.50
    Then
    0.49
    ersen
    0.49
    Act Density 0.231%

    No Known Activations