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

    Neuronpedia

    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¤ł
    -0.24
    å¸ĮæľĽå¤§å®¶
    -0.24
    tool
    -0.23
    upon
    -0.22
    åIJĦçķĮ
    -0.21
    说ä¸įåĩº
    -0.21
    大éĥ¨åĪĨ人
    -0.21
     Abed
    -0.21
     Dai
    -0.21
    anal
    -0.21
    POSITIVE LOGITS
    zzo
    0.26
    erness
    0.26
    recht
    0.26
    -start
    0.25
     Weg
    0.25
    prit
    0.24
    EX
    0.24
    .Start
    0.23
    çīĻ
    0.23
     tension
    0.23
    Act Density 1.837%

    No Known Activations