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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ई
    -0.07
    	files
    -0.06
    OWNER
    -0.06
     SOAP
    -0.06
    apan
    -0.06
    macen
    -0.06
     сор
    -0.06
    ISTORY
    -0.06
    "w
    -0.06
    _Begin
    -0.06
    POSITIVE LOGITS
      ↵
    0.07
    nerRadius
    0.06
    ことに
    0.06
    Fuel
    0.06
    0.06
    names
    0.06
     ade
    0.06
    comparison
    0.06
    trak
    0.06
     opening
    0.06
    Act Density 0.052%

    No Known Activations