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

    Neuronpedia

    INDEX
    Explanations

    awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obras
    -0.07
     '['
    -0.06
    手を
    -0.06
    (",")↵
    -0.06
    ＼:
    -0.06
    模型
    -0.06
    anol
    -0.06
     mour
    -0.06
     landslide
    -0.06
     chipset
    -0.06
    POSITIVE LOGITS
     WARN
    0.07
    addAll
    0.06
     kho
    0.06
     insanely
    0.06
     combine
    0.06
    	w
    0.06
    (URL
    0.06
    ailand
    0.06
    меть
    0.06
    ểm
    0.06
    Act Density 0.017%

    No Known Activations