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

    Neuronpedia

    INDEX
    Explanations

    statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Antarctic
    -0.07
    えた
    -0.07
    те
    -0.06
     rails
    -0.06
     至
    -0.06
    pectral
    -0.06
    etre
    -0.06
    elib
    -0.06
    776
    -0.06
    .gz
    -0.06
    POSITIVE LOGITS
     them
    0.07
     دفتر
    0.07
    全面
    0.06
    (enemy
    0.06
     jugg
    0.06
     TMPro
    0.06
     Portable
    0.06
     Minority
    0.06
     Dem
    0.06
     deficient
    0.06
    Act Density 0.010%

    No Known Activations