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

    Neuronpedia

    INDEX
    Explanations

    When followed by a pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അപ
    0.39
    жалуйста
    0.38
     পাঠিয়ে
    0.38
    änder
    0.38
    てください
    0.38
    літи
    0.38
    예
    0.38
     Days
    0.37
    实的
    0.37
    %
    0.37
    POSITIVE LOGITS
    izr
    0.47
     alimento
    0.44
    ।
    0.43
     crimin
    0.41
     मृ
    0.41
     pisc
    0.39
     culinary
    0.39
     potencia
    0.39
     econ
    0.39
     Qué
    0.38
    Act Density 0.000%

    No Known Activations