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

    Neuronpedia

    INDEX
    Explanations

    code and coding standards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaking
    -0.07
     find
    -0.07
     GPU
    -0.07
    (m
    -0.06
    Towards
    -0.06
    _meter
    -0.06
    -ac
    -0.06
     ahead
    -0.06
    :_
    -0.06
     vertices
    -0.06
    POSITIVE LOGITS
    「……
    0.06
    fef
    0.06
    .compareTo
    0.06
     Appalachian
    0.06
     كور
    0.06
     geil
    0.06
     běž
    0.06
    ocyte
    0.06
     अवध
    0.06
     ži
    0.06
    Act Density 0.010%

    No Known Activations