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

    Neuronpedia

    INDEX
    Explanations

    list of items and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ít
    0.29
     môn
    0.29
     lanz
    0.29
     Amir
    0.29
     biotechnology
    0.29
     fom
    0.29
     people
    0.28
     it
    0.28
     Michael
    0.28
     agriculture
    0.28
    POSITIVE LOGITS
    ཎ
    0.36
    Стра
    0.36
    Су
    0.36
    Га
    0.36
    ミ
    0.36
    В
    0.35
    6
    0.35
    리
    0.35
    ד
    0.35
    ७
    0.35
    Act Density 1.230%

    No Known Activations