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

    Neuronpedia

    INDEX
    Explanations

    disturbing shadows; weaknesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক্ষিতে
    0.38
    افئ
    0.38
    ाइब
    0.37
    蒎
    0.36
     সাহায্য
    0.36
     suppressor
    0.36
     annum
    0.36
     '/',
    0.36
    阀
    0.36
     FERC
    0.36
    POSITIVE LOGITS
    test
    0.47
    comput
    0.46
     deta
    0.46
     maiores
    0.46
    mod
    0.46
     visar
    0.44
     पछ
    0.44
     maç
    0.44
    ní
    0.43
     Editions
    0.43
    Act Density 0.001%

    No Known Activations