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

    Neuronpedia

    INDEX
    Explanations

    tracking over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wors
    -0.08
     disaster
    -0.07
     Tak
    -0.07
    Processing
    -0.07
    Word
    -0.06
     Garden
    -0.06
    -information
    -0.06
    ��
    -0.06
     unlucky
    -0.06
    istik
    -0.06
    POSITIVE LOGITS
    ([],
    0.07
     предус
    0.07
     هنگام
    0.06
    .ncbi
    0.06
    SupportFragmentManager
    0.06
    ederation
    0.06
    _paragraph
    0.06
    _RCC
    0.06
    -Javadoc
    0.06
     els
    0.06
    Act Density 0.047%

    No Known Activations