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

    Neuronpedia

    INDEX
    Explanations

    Country, Age, Local

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    environment
    0.59
    ي
    0.57
    х
    0.57
     と
    0.56
    }+\
    0.54
    д
    0.52
    和
    0.52
    }+
    0.51
     如果
    0.50
     opravdu
    0.50
    POSITIVE LOGITS
    ighton
    0.49
    ﻊ
    0.49
    ENCI
    0.46
     Kaye
    0.46
    اصل
    0.45
     footh
    0.44
    मध्ये
    0.44
    apeake
    0.44
    pati
    0.43
     Smoky
    0.43
    Act Density 0.001%

    No Known Activations