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

    Neuronpedia

    INDEX
    Explanations

    variable and type declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ها
    0.43
    ed
    0.39
    :
    0.38
    embangan
    0.31
     heightened
    0.31
    வுக்கு
    0.31
    อย่างไร
    0.31
    ის
    0.30
     dõi
    0.30
    versive
    0.30
    POSITIVE LOGITS
     Álvarez
    0.33
    č
    0.32
     vâr
    0.31
     riječi
    0.31
     약
    0.31
    志森
    0.30
     ק
    0.30
     k
    0.29
     isOpen
    0.29
     Ко
    0.29
    Act Density 0.274%

    No Known Activations