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

    Neuronpedia

    INDEX
    Explanations

    cross for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ước
    1.66
    الف
    1.45
     trava
    1.45
    и
    1.45
     endoplasmic
    1.45
    От
    1.43
     aeg
    1.43
    volving
    1.42
     cytoplasm
    1.38
     Cyborg
    1.37
    POSITIVE LOGITS
    덴
    1.22
    了一个
    1.08
     ""))
    1.07
    ...+
    1.06
    /=
    1.04
    帜
    1.02
    ER
    1.02
    ケット
    1.01
    ع
    1.01
    ਹੁ
    0.99
    Act Density 0.001%

    No Known Activations