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

    Neuronpedia

    INDEX
    Explanations

    error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.67
    Via
    0.57
    Ch
    0.56
    USA
    0.55
    Dedicated
    0.55
     (
    0.55
     দশ
    0.55
    IT
    0.54
    Tend
    0.54
    Round
    0.52
    POSITIVE LOGITS
     δεν
    1.09
     не
    1.05
     没有
    1.05
     invál
    1.04
    不能为空
    1.04
     ਨਹੀਂ
    1.03
     немає
    1.03
     không
    1.02
     není
    1.02
     cannot
    1.00
    Act Density 0.040%

    No Known Activations