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

    Neuronpedia

    INDEX
    Explanations

    impaired judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.28
    im
    1.11
    ar
    1.04
    en
    1.02
    1
    1.02
    P
    0.98
    8
    0.95
    ed
    0.95
    an
    0.92
    с
    0.91
    POSITIVE LOGITS
    ◃
    0.94
    TextureData
    0.90
     remarquable
    0.88
    匾
    0.88
    ພວກເຮ
    0.87
     šte
    0.87
     chalkboard
    0.86
     stabilité
    0.86
     siècles
    0.86
     bianco
    0.86
    Act Density 0.000%

    No Known Activations