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

    Neuronpedia

    INDEX
    Explanations

    control over parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grpc
    1.29
     neurotrans
    1.25
    únior
    1.24
    ্তি
    1.24
    вости
    1.23
    ্তির
    1.20
     Kyrgios
    1.19
     eukaryotes
    1.18
    гүнкү
    1.17
     propeller
    1.17
    POSITIVE LOGITS
    로
    1.34
    ات
    1.34
    ル
    1.31
    তে
    1.30
    在
    1.30
    에
    1.23
    路
    1.19
    اگر
    1.11
    ও
    1.09
    ם
    1.09
    Act Density 0.000%

    No Known Activations