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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NES
    -0.07
    348
    -0.07
    315
    -0.06
     shifted
    -0.06
    开展
    -0.06
     πα
    -0.06
     thất
    -0.06
    140
    -0.06
    ообраз
    -0.06
    EXP
    -0.06
    POSITIVE LOGITS
     isVisible
    0.07
    Recommend
    0.07
     norm
    0.07
     trademarks
    0.07
    Scope
    0.07
     Administrator
    0.06
    —I
    0.06
     AssemblyProduct
    0.06
    인
    0.06
    (expect
    0.06
    Act Density 0.050%

    No Known Activations