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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or amusement

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

    smile and laugh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vPvB
    -0.42
    rrggbb
    -0.37
    voerd
    -0.36
     bluzka
    -0.36
     extérieure
    -0.36
     affinch
    -0.35
     imprimée
    -0.35
    IntoConstraints
    -0.35
     eenig
    -0.35
    élément
    -0.34
    POSITIVE LOGITS
    笑
    1.09
     laughing
    1.03
     Laughing
    0.96
     笑
    0.95
     laughed
    0.94
    laughing
    0.88
    Laughing
    0.87
     laughter
    0.85
     Laughter
    0.80
     laugh
    0.79
    Act Density 0.005%

    No Known Activations