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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duction
    -0.07
    _cmd
    -0.06
     monkeys
    -0.06
    Started
    -0.06
    onn
    -0.06
     Kont
    -0.06
     Polly
    -0.06
    щини
    -0.06
     build
    -0.06
    (em
    -0.06
    POSITIVE LOGITS
    下来
    0.07
     été
    0.07
     Origin
    0.06
     activist
    0.06
     مث
    0.06
     İş
    0.06
    	word
    0.06
     ",↵
    0.06
    Cow
    0.06
    μήμα
    0.06
    Act Density 0.003%

    No Known Activations