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

    Neuronpedia

    INDEX
    Explanations

    please provide me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    咱们
    0.96
    咱們
    0.94
    咱
    0.93
    讓我們
    0.90
     comfy
    0.89
    :";
    0.86
    让我们
    0.80
    気軽
    0.77
     we
    0.77
     чисто
    0.76
    POSITIVE LOGITS
     cannot
    1.02
     невозможно
    0.86
    cannot
    0.83
     Cannot
    0.82
    Cannot
    0.78
    を参照
    0.76
     necesario
    0.75
     trebuie
    0.75
     entferne
    0.74
    não
    0.72
    Act Density 0.205%

    No Known Activations