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

    Neuronpedia

    INDEX
    Explanations

    input/output operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delivered
    0.40
    dbjc
    0.39
    thorpe
    0.39
    étique
    0.38
    ър
    0.38
    ليك
    0.38
    thoughts
    0.38
     Coke
    0.38
     కళ
    0.38
    णाली
    0.38
    POSITIVE LOGITS
     IO
    0.72
    IOException
    0.69
    IO
    0.68
    Io
    0.64
     Io
    0.61
    IOD
    0.60
     ioe
    0.55
     io
    0.55
    IOT
    0.55
     iod
    0.54
    Act Density 0.012%

    No Known Activations