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

    Neuronpedia

    INDEX
    Explanations

    people might feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    1.88
    ag
    1.85
    ig
    1.81
    il
    1.75
    _
    1.64
    ️
    1.63
    เป็น
    1.62
    ary
    1.60
    aters
    1.59
     nghiệm
    1.59
    POSITIVE LOGITS
     publiques
    1.96
    hips
    1.80
    ዬ
    1.78
    ки
    1.77
     slags
    1.73
     erythematosus
    1.71
     olefins
    1.69
     chinois
    1.59
    蔘
    1.59
    льным
    1.57
    Act Density 0.311%

    No Known Activations