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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temperament
    -0.07
     ranch
    -0.07
    _alignment
    -0.06
     intellect
    -0.06
     obedience
    -0.06
     uploader
    -0.06
    儀
    -0.06
     logically
    -0.06
    .AddRange
    -0.06
    えない
    -0.06
    POSITIVE LOGITS
     Fr
    0.07
    っぱい
    0.06
    bsite
    0.06
     reserve
    0.06
    Containing
    0.06
     Fiona
    0.06
     ді
    0.06
     shedding
    0.06
    hread
    0.06
    .Stderr
    0.06
    Act Density 0.013%

    No Known Activations