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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setParent
    -0.07
     compact
    -0.07
    滋润
    -0.07
    去过
    -0.07
    샤
    -0.07
    团结
    -0.07
     każdy
    -0.07
    #!/
    -0.07
     nutritional
    -0.07
     tar
    -0.07
    POSITIVE LOGITS
     centers
    0.07
    下跌
    0.07
     acab
    0.07
    Unix
    0.06
     Undefined
    0.06
     Quiz
    0.06
    (second
    0.06
    OP
    0.06
    盷
    0.06
     NF
    0.06
    Act Density 0.001%

    No Known Activations