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

    Neuronpedia

    INDEX
    Explanations

    brand names L'Oréal, John Deere, Indeed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.73
    ta
    0.69
    transforms
    0.64
    rát
    0.64
    ted
    0.64
    t
    0.64
    tom
    0.63
    tes
    0.63
    tout
    0.63
    жом
    0.63
    POSITIVE LOGITS
     in
    1.11
    是
    1.00
    在
    0.95
    ۔
    0.91
    ة
    0.79
    는
    0.75
    도
    0.75
    も
    0.71
    但是
    0.71
    С
    0.69
    Act Density 0.001%

    No Known Activations