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

    Neuronpedia

    INDEX
    Explanations

    expressions of joy and affection, particularly smiles and laughter

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

    smiling

    np_acts-logits-general · gemini-2.0-flash

    smile and grin expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.69
    ixos
    -0.60
    市镇
    -0.57
    optString
    -0.56
     Hov
    -0.55
     deberes
    -0.54
     trattano
    -0.53
    nationality
    -0.50
     législ
    -0.50
    Gön
    -0.49
    POSITIVE LOGITS
    BagConstraints
    0.62
     CreateTagHelper
    0.60
     SMI
    0.60
    InputTagHelper
    0.59
     plastered
    0.59
     smile
    0.59
     wry
    0.59
    GOTREF
    0.58
     Smile
    0.57
    Smiles
    0.57
    Act Density 0.036%

    No Known Activations