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

    Neuronpedia

    INDEX
    Explanations

    Periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xis
    -0.08
     применя
    -0.07
    467
    -0.07
    >v
    -0.07
    unset
    -0.06
    869
    -0.06
     Ис
    -0.06
     желез
    -0.06
     improvis
    -0.06
    879
    -0.06
    POSITIVE LOGITS
     Id
    0.07
     Deals
    0.07
    .timeScale
    0.07
    ermen
    0.07
     Philly
    0.06
    Reference
    0.06
    bers
    0.06
    "id
    0.06
     Population
    0.06
     جن
    0.06
    Act Density 0.050%

    No Known Activations