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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases that indicate dialogue or exchanges between characters

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

    words that start clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iconTwitter
    -0.46
    createCanvas
    -0.45
    astéroïdes
    -0.43
    -0.42
    цездатний
    -0.41
     désolés
    -0.40
    StoryboardSegue
    -0.39
    脚注の使い方
    -0.39
     Exacts
    -0.38
    něte
    -0.37
    POSITIVE LOGITS
     صوتيه
    0.57
    ########.
    0.54
     Biôgrafia
    0.45
    principalColumn
    0.44
    bitField
    0.41
     glaubte
    0.40
     تضيفلها
    0.40
    lixir
    0.40
     CWE
    0.39
     moeite
    0.39
    Act Density 0.193%

    No Known Activations