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

    Neuronpedia

    INDEX
    Explanations

    that being said, initial thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.16
    */
    1.12
    ard
    1.04
     Straße
    0.99
    дм
    0.96
    اط
    0.96
    اق
    0.96
    tag
    0.95
    انک
    0.94
    ے
    0.93
    POSITIVE LOGITS
    ת
    1.70
     morbidity
    1.58
     notions
    1.56
    יות
    1.56
    𝚋
    1.54
    ة
    1.53
    xcuser
    1.53
     unfounded
    1.51
     mathematical
    1.50
     appearances
    1.49
    Act Density 0.000%

    No Known Activations