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

    Neuronpedia

    INDEX
    Explanations

    Casual, emphatic language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     establish
    -0.09
    _swap
    -0.08
    edi
    -0.07
    /A
    -0.07
    StringUtils
    -0.07
    ModelAttribute
    -0.07
     spontaneously
    -0.07
    Develop
    -0.07
     established
    -0.06
     irregular
    -0.06
    POSITIVE LOGITS
    unik
    0.07
     Lesson
    0.07
    аток
    0.06
    真是
    0.06
     Hope
    0.06
     کلی
    0.06
     Alzheimer
    0.06
     Kraj
    0.05
     offense
    0.05
     엔
    0.05
    Act Density 0.012%

    No Known Activations