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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Label
    -0.07
    帮
    -0.07
     듯
    -0.07
     teaspoons
    -0.07
    nosis
    -0.06
    екс
    -0.06
    �
    -0.06
     rinse
    -0.06
    ザイン
    -0.06
    -work
    -0.06
    POSITIVE LOGITS
    -strokes
    0.07
     Greenwich
    0.06
     Jupiter
    0.06
    decrypt
    0.06
    IGNED
    0.06
    _exchange
    0.06
    ='./
    0.06
    favorites
    0.06
     chăm
    0.06
    738
    0.06
    Act Density 0.054%

    No Known Activations