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

    Neuronpedia

    INDEX
    Explanations

    foreign language, specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    把它
    0.47
    しかも
    0.42
    在其
    0.40
    为其
    0.37
    将其
    0.37
    在你
    0.37
    inie
    0.36
    igma
    0.36
    改为
    0.36
    itsa
    0.36
    POSITIVE LOGITS
     あの
    0.56
     Notably
    0.55
    那個
    0.54
     отдельно
    0.54
     Regarding
    0.53
     Items
    0.52
     those
    0.49
     regarding
    0.49
    那个
    0.49
     těch
    0.49
    Act Density 0.015%

    No Known Activations