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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _phr
    -0.07
     bais
    -0.07
    forest
    -0.06
    .Symbol
    -0.06
    	url
    -0.06
     �
    -0.06
     fluids
    -0.06
    acters
    -0.06
    .jar
    -0.06
     intuition
    -0.06
    POSITIVE LOGITS
    rtle
    0.07
     المعلومات
    0.07
    .transparent
    0.06
     jíd
    0.06
    infer
    0.06
    ↵↵↵↵↵↵
    0.06
    643
    0.06
     Appalachian
    0.06
     comida
    0.06
    /cards
    0.06
    Act Density 0.024%

    No Known Activations