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

    Neuronpedia

    INDEX
    Explanations

    unsorted portion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.57
     that
    0.45
     percor
    0.45
     framework
    0.44
     It
    0.43
     dir
    0.43
     descrizione
    0.43
    p
    0.43
     classifica
    0.42
     That
    0.42
    POSITIVE LOGITS
    ઉસ
    0.49
    ას
    0.49
    ନ
    0.48
     انتقال
    0.47
    Initialization
    0.46
    يش
    0.46
    нія
    0.45
    િંગ
    0.45
    ető
    0.45
    აციის
    0.45
    Act Density 0.001%

    No Known Activations