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

    Neuronpedia

    INDEX
    Explanations

    menu items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     increments
    0.45
     crystallinity
    0.44
    怿
    0.41
     defer
    0.40
    裁剪
    0.40
    érus
    0.40
    दन
    0.40
     heredit
    0.40
     mutex
    0.39
     subordination
    0.39
    POSITIVE LOGITS
     Chicken
    1.17
    Chicken
    1.16
     chicken
    1.09
     Shrimp
    1.05
     Grilled
    1.04
     grilled
    1.02
     fried
    1.01
     spicy
    1.01
     Spicy
    1.01
    Grilled
    0.98
    Act Density 0.069%

    No Known Activations