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

    Neuronpedia

    INDEX
    Explanations

    Local

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stayed
    -0.07
    lish
    -0.06
    Articles
    -0.06
    ishly
    -0.06
     Witness
    -0.06
    ν
    -0.06
    'il
    -0.06
    ْل
    -0.06
     accidents
    -0.06
    276
    -0.06
    POSITIVE LOGITS
     пока
    0.08
     Kazakhstan
    0.08
    (Expected
    0.07
     الرياض
    0.07
     déjà
    0.07
    ################################################################
    0.07
     enumerate
    0.07
     forControlEvents
    0.06
    Existing
    0.06
    であり
    0.06
    Act Density 0.009%

    No Known Activations