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

    Neuronpedia

    INDEX
    Explanations

    instances of concluding, discussing, and presenting.

    oai_token-act-pair · gemini-2.0-flash

    conclude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typelib
    -0.84
     AssemblyProduct
    -0.83
     "..\..\..\
    -0.80
    ValueStyle
    -0.78
    Hentet
    -0.75
    WriteTagHelper
    -0.74
    MemoryWarning
    -0.73
     <=",
    -0.72
    StateList
    -0.71
    UnusedPrivate
    -0.71
    POSITIVE LOGITS
     about
    0.51
     veneta
    0.46
    外的
    0.46
     segni
    0.45
     we
    0.44
    dowa
    0.43
     hangs
    0.43
    قایناق‌لار
    0.42
    作品
    0.42
     signs
    0.42
    Act Density 4.198%

    No Known Activations