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

    Neuronpedia

    INDEX
    Explanations

    PIL and risk assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IZ
    0.45
    دا
    0.44
    יי
    0.44
     enough
    0.43
     ಯಾವುದ
    0.43
    hij
    0.42
    Hij
    0.42
    驄
    0.42
    מש
    0.41
    ailure
    0.41
    POSITIVE LOGITS
     Gr
    0.44
     ምክንያት
    0.43
     μαζί
    0.43
    相互
    0.41
     যথার্থ
    0.41
     акысыз
    0.39
    chette
    0.39
     povez
    0.39
     படை
    0.39
     પ્રા
    0.39
    Act Density 0.000%

    No Known Activations