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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alternatives
    -0.08
     capacitor
    -0.07
    离职
    -0.07
    最好是
    -0.07
    addAll
    -0.06
    >You
    -0.06
    一一
    -0.06
    dept
    -0.06
     passport
    -0.06
    也就
    -0.06
    POSITIVE LOGITS
     Gry
    0.08
    中国人民
    0.07
    .rf
    0.07
    (FLAGS
    0.07
     RandomForest
    0.07
    CBS
    0.06
     CST
    0.06
    RPC
    0.06
     chili
    0.06
    	Config
    0.06
    Act Density 0.000%

    No Known Activations