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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usb
    -0.07
    relu
    -0.07
    -ui
    -0.06
    ですが
    -0.06
    興
    -0.06
    問題
    -0.06
     têm
    -0.06
    peace
    -0.06
    Water
    -0.06
    	writer
    -0.06
    POSITIVE LOGITS
    เปล
    0.06
     실제
    0.06
     ".$_
    0.06
     formatting
    0.06
     proclaimed
    0.06
     Brilliant
    0.06
     familiarity
    0.06
    、あ
    0.06
     �
    0.06
    .setScale
    0.06
    Act Density 0.036%

    No Known Activations