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

    Neuronpedia

    INDEX
    Explanations

    slov

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     安
    -0.08
     NR
    -0.07
    272
    -0.07
     Kant
    -0.07
     Raf
    -0.07
     Gy
    -0.07
    	router
    -0.06
     Sonic
    -0.06
     reputation
    -0.06
    374
    -0.06
    POSITIVE LOGITS
     Bloom
    0.07
    �
    0.07
     Flo
    0.07
     Flores
    0.07
    drops
    0.07
     �
    0.06
    ضافة
    0.06
     네이트온
    0.06
    궁
    0.06
     داو
    0.06
    Act Density 0.046%

    No Known Activations