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

    Neuronpedia

    INDEX
    Explanations

    Caesar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conc
    -0.07
     Offers
    -0.07
    getRoot
    -0.07
    neh
    -0.07
     Forum
    -0.06
    手机版
    -0.06
    Comb
    -0.06
     Urg
    -0.06
     Universities
    -0.06
    律
    -0.06
    POSITIVE LOGITS
     ding
    0.08
    (socket
    0.07
    שאל
    0.07
    цикл
    0.07
    	expect
    0.07
    (vm
    0.07
    "If
    0.07
    ActionCreators
    0.07
     weakening
    0.06
     wida
    0.06
    Act Density 0.007%

    No Known Activations