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

    Neuronpedia

    INDEX
    Explanations

    Encoder usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ogloss
    0.71
    ogast
    0.69
     الو
    0.67
     پوس
    0.65
     registration
    0.63
    デオ
    0.62
     στά
    0.62
    ೋಜ
    0.61
    Ante
    0.61
    CallSettings
    0.61
    POSITIVE LOGITS
    ad
    1.10
     ad
    1.03
    Ad
    1.03
     Ad
    0.99
    AD
    0.92
     AD
    0.83
    adera
    0.80
    adia
    0.76
     Advent
    0.76
    ادا
    0.75
    Act Density 0.170%

    No Known Activations