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

    Neuronpedia

    INDEX
    Explanations

    politico, politician, politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.84
    at
    0.79
    s
    0.74
    ا
    0.73
    نا
    0.71
    a
    0.69
    na
    0.69
    ب
    0.68
    ao
    0.68
    नंतर
    0.68
    POSITIVE LOGITS
     be
    0.62
     Frau
    0.61
     grove
    0.61
     riche
    0.61
     différentes
    0.60
     groei
    0.60
     sotto
    0.58
     spezi
    0.58
    的文件
    0.57
     lò
    0.56
    Act Density 0.000%

    No Known Activations