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

    Neuronpedia

    INDEX
    Explanations

    professions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.22
     تضيفلها
    -1.14
     enfans
    -1.12
    WebElementEntity
    -1.09
     feroit
    -1.06
     '\\;'
    -1.02
     pouvoit
    -1.01
    IUrlHelper
    -1.01
     attacker
    -1.00
     étoient
    -0.99
    POSITIVE LOGITS
    '
    1.33
    ’
    1.22
     who
    0.94
    (
    0.90
    less
    0.89
    ial
    0.88
    ss
    0.84
     of
    0.76
    ate
    0.74
    /
    0.74
    Act Density 0.771%

    No Known Activations