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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edgar
    -0.07
     Aval
    -0.07
    /wait
    -0.07
     Translation
    -0.07
    なく
    -0.06
    -console
    -0.06
    室
    -0.06
    .dot
    -0.06
    ListOf
    -0.06
    folder
    -0.06
    POSITIVE LOGITS
     PUBLIC
    0.07
    reich
    0.07
     hearty
    0.07
    ڽ
    0.07
    .scalajs
    0.07
     districts
    0.07
    闫
    0.07
     Brom
    0.07
    .currentState
    0.07
     sectarian
    0.07
    Act Density 0.007%

    No Known Activations