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

    Neuronpedia

    INDEX
    Explanations

    All

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FOUND
    -0.07
     及
    -0.07
    층의
    -0.06
     ware
    -0.06
     VI
    -0.06
     Ven
    -0.06
    782
    -0.06
     III
    -0.06
    After
    -0.06
     کننده
    -0.06
    POSITIVE LOGITS
     All
    0.08
     Lennon
    0.08
    All
    0.07
     all
    0.06
    (isinstance
    0.06
    .ordinal
    0.06
    MBProgressHUD
    0.06
    кус
    0.06
    enever
    0.06
     nella
    0.06
    Act Density 0.002%

    No Known Activations