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

    Neuronpedia

    INDEX
    Explanations

    approximately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    7
    -0.08
     Hand
    -0.07
    170
    -0.07
     TableName
    -0.07
     hands
    -0.07
     win
    -0.06
    70
    -0.06
     heads
    -0.06
     hand
    -0.06
     Ter
    -0.06
    POSITIVE LOGITS
     approximately
    0.12
     Approximately
    0.10
    approximately
    0.09
     approx
    0.09
    APA
    0.08
    apis
    0.08
    approx
    0.08
    約
    0.07
    graph
    0.07
    erva
    0.07
    Act Density 0.011%

    No Known Activations