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

    Neuronpedia

    INDEX
    Explanations

    client

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dub
    -0.07
    词
    -0.07
    spa
    -0.07
     subdiv
    -0.07
    驱
    -0.07
     wol
    -0.06
    struct
    -0.06
    STREAM
    -0.06
    nombre
    -0.06
    -monitor
    -0.06
    POSITIVE LOGITS
    Happy
    0.08
     restTemplate
    0.07
    俫
    0.07
    狈
    0.07
    圆满
    0.07
     Affairs
    0.07
     '');
    0.07
     entails
    0.06
    .easy
    0.06
    composite
    0.06
    Act Density 0.053%

    No Known Activations