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

    Neuronpedia

    INDEX
    Explanations

    frequencies vary with time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кі
    0.47
     فری
    0.46
    ита
    0.44
    ཊ
    0.43
     النفس
    0.41
     clowns
    0.40
    ᑐ
    0.40
     ફ
    0.40
    ロナ
    0.39
     ф
    0.39
    POSITIVE LOGITS
     Ayer
    0.40
    ichtlich
    0.38
     BIOS
    0.38
     rice
    0.38
    ಗದ
    0.38
     glau
    0.37
     airy
    0.37
     blends
    0.36
     mixes
    0.36
     timetable
    0.36
    Act Density 0.000%

    No Known Activations