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
    少了
    -0.08
    enor
    -0.07
    近视
    -0.07
     responses
    -0.07
     attractions
    -0.07
    缞
    -0.07
    醌
    -0.07
    model
    -0.07
    ottenham
    -0.07
     porta
    -0.07
    POSITIVE LOGITS
    -disc
    0.07
    考量
    0.07
     volley
    0.07
    /W
    0.07
     Likewise
    0.06
     urlparse
    0.06
    意图
    0.06
    .U
    0.06
     constitutes
    0.06
    讲解
    0.06
    Act Density 0.049%

    No Known Activations