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

    Neuronpedia

    INDEX
    Explanations

    Zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getting
    -0.08
     त्यामुळे
    -0.08
    nergies
    -0.08
     Opportunities
    -0.07
    owered
    -0.07
    _names
    -0.07
     അത
    -0.07
    Names
    -0.07
     suspect
    -0.07
    ไม่มี
    -0.07
    POSITIVE LOGITS
     ję
    0.09
     языке
    0.08
     kcal
    0.08
     modulo
    0.08
     respecto
    0.07
     wata
    0.07
    Cape
    0.07
    ]_
    0.07
     fiduci
    0.07
    %的
    0.07
    Act Density 0.019%

    No Known Activations