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

    Neuronpedia

    INDEX
    Explanations

    sc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     каждого
    -0.06
    Version
    -0.06
    *R
    -0.06
    た
    -0.06
    EventManager
    -0.06
    .rb
    -0.06
    ึกษา
    -0.06
     Вал
    -0.06
    #c
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
     Dress
    0.07
    	router
    0.07
     demand
    0.06
     Benghazi
    0.06
    stuff
    0.06
     круп
    0.06
     cooked
    0.06
     mortal
    0.06
    �
    0.06
    chain
    0.06
    Act Density 0.004%

    No Known Activations