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

    Neuronpedia

    INDEX
    Explanations

    familiar with, ashamed or, protecting dissenting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Admin
    0.55
     admin
    0.45
     barcodes
    0.43
    有多少
    0.43
     administrat
    0.42
    Elemental
    0.41
     είχε
    0.41
    Auto
    0.40
    &
    0.40
    గ
    0.40
    POSITIVE LOGITS
    tired
    0.52
     রিলিফ
    0.47
     numéro
    0.45
     டிர
    0.45
    انی
    0.44
    ارو
    0.44
    넷
    0.44
    コーヒー
    0.44
     rétro
    0.44
     myCamera
    0.43
    Act Density 0.001%

    No Known Activations