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

    Neuronpedia

    INDEX
    Explanations

    alternate dimensions and worlds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trois
    0.53
     சுற்றுச்சூழல்
    0.52
     разработан
    0.52
     üç
    0.52
     நான்கு
    0.52
     dạy
    0.52
     drei
    0.51
     porté
    0.49
    运行时
    0.49
    高兴
    0.49
    POSITIVE LOGITS
    import
    0.56
     India
    0.54
    {~
    0.53
    ad
    0.52
    ド
    0.52
    select
    0.52
    Down
    0.51
     Append
    0.51
    Привет
    0.51
    ड्डी
    0.50
    Act Density 0.020%

    No Known Activations