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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cfg
    -0.06
     fire
    -0.06
     timber
    -0.06
    棚
    -0.06
    ยง
    -0.06
    igid
    -0.06
     얻
    -0.06
    :{}
    -0.06
     JFrame
    -0.06
    _category
    -0.06
    POSITIVE LOGITS
    :UIControlEvent
    0.08
    ifdef
    0.07
    .IDENTITY
    0.06
     presumably
    0.06
     sperma
    0.06
    udos
    0.06
     wor
    0.06
    ỉnh
    0.06
    hello
    0.06
     зуп
    0.06
    Act Density 0.001%

    No Known Activations