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

    Neuronpedia

    INDEX
    Explanations

    processes and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swoich
    0.68
     teljesen
    0.66
     alles
    0.65
    ເປັນ
    0.65
     jedną
    0.65
     ಎಲ್ಲಾ
    0.64
     svých
    0.64
     completamente
    0.63
     képes
    0.63
     casket
    0.62
    POSITIVE LOGITS
    การ
    1.71
     การ
    1.39
    ການ
    1.33
     việc
    1.32
     creation
    1.21
    ការ
    1.18
     removal
    1.14
     використання
    1.12
     criação
    1.12
     ການ
    1.11
    Act Density 0.166%

    No Known Activations