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

    Neuronpedia

    INDEX
    Explanations

    answer questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualquer
    0.81
    任何
    0.80
     Any
    0.77
     这里
    0.75
     herhangi
    0.75
     quaisquer
    0.73
    anything
    0.73
     något
    0.72
    Any
    0.72
     ছবিটি
    0.71
    POSITIVE LOGITS
     respect
    1.02
    respect
    0.95
    ້ອ
    0.94
     dignified
    0.92
    گانی
    0.87
     immediate
    0.83
    жидан
    0.82
    ères
    0.82
    抱怨
    0.82
     तुरंत
    0.81
    Act Density 0.001%

    No Known Activations