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

    Neuronpedia

    INDEX
    Explanations

    leading us to reject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ј
    0.54
    ównie
    0.51
     име
    0.48
     ისინი
    0.48
    hubungan
    0.47
    attamente
    0.47
     обратиться
    0.46
    飛行
    0.44
    眾
    0.44
    getResource
    0.43
    POSITIVE LOGITS
     teeth
    0.47
     Cal
    0.46
     Redis
    0.46
     Dent
    0.46
     AB
    0.45
     Leads
    0.45
     Teeth
    0.44
     Callable
    0.44
     Ala
    0.44
     untouched
    0.44
    Act Density 0.013%

    No Known Activations