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

    Neuronpedia

    INDEX
    Explanations

    different languages and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ול
    0.30
    Toplam
    0.30
    所有的
    0.28
    АР
    0.28
    メ
    0.28
    ATE
    0.28
    שת
    0.28
    Toto
    0.28
    не
    0.28
    েলি
    0.28
    POSITIVE LOGITS
     înd
    0.32
     Darüber
    0.30
     similar
    0.30
     într
    0.30
    lej
    0.29
    ].
    0.28
    ).
    0.27
    .).
    0.27
     Brighton
    0.27
     February
    0.27
    Act Density 0.119%

    No Known Activations