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

    Neuronpedia

    INDEX
    Explanations

    facial expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    创建
    0.82
    跳转
    0.79
     workflows
    0.79
    ímenes
    0.78
    权限
    0.78
    เภท
    0.78
     ঝামে
    0.76
    policies
    0.75
     편리
    0.75
     interoper
    0.75
    POSITIVE LOGITS
     smile
    2.73
     facial
    2.60
     smiling
    2.41
     smiles
    2.36
     smiled
    2.36
     Facial
    2.23
     sorriso
    2.20
    表情
    2.20
     Smile
    2.06
    smiling
    2.02
    Act Density 0.533%

    No Known Activations