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

    Neuronpedia

    INDEX
    Explanations

    Eritrea and related geographical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一
    1.01
    大
    0.92
    ли
    0.90
    ρα
    0.89
    ra
    0.88
    리
    0.85
    वा
    0.83
    자
    0.82
    ра
    0.81
    ai
    0.81
    POSITIVE LOGITS
     leurs
    0.86
     leur
    0.79
     você
    0.74
     njihov
    0.73
    ların
    0.72
     jejich
    0.71
     povos
    0.71
     kanë
    0.71
     pě
    0.71
     vaš
    0.69
    Act Density 0.003%

    No Known Activations