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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diamonds
    -0.07
    Long
    -0.07
     Dist
    -0.07
    (isset
    -0.07
    巨额
    -0.07
    辦理
    -0.07
    唐
    -0.07
     dis
    -0.07
     Neg
    -0.06
    (dummy
    -0.06
    POSITIVE LOGITS
     når
    0.07
    핸
    0.07
     Parent
    0.06
    /java
    0.06
     THROUGH
    0.06
    趁着
    0.06
    翮
    0.06
    岗位
    0.06
     getPath
    0.06
     Kal
    0.06
    Act Density 0.016%

    No Known Activations