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

    Neuronpedia

    INDEX
    Explanations

    choice or option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نه
    0.55
    .
    0.54
    __
    0.52
     encuentro
    0.52
    네
    0.52
    lib
    0.51
    _
    0.51
     व्हाउचर
    0.50
    이
    0.49
     сериа
    0.49
    POSITIVE LOGITS
     RATE
    0.46
     নাই
    0.45
     ………………………………..
    0.44
    ಿತಿ
    0.43
     $:=$
    0.43
     .)
    0.43
    矨
    0.43
    ត្
    0.42
     '/')
    0.42
     VOICE
    0.42
    Act Density 0.001%

    No Known Activations