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

    Neuronpedia

    INDEX
    Explanations

    brand identity and marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.96
    ла
    0.95
     сдела
    0.91
     начинается
    0.90
    в
    0.89
     потому
    0.88
    lar
    0.86
     politica
    0.86
     действует
    0.86
     escrito
    0.84
    POSITIVE LOGITS
     I
    1.14
    ار
    1.11
    ur
    1.09
    ir
    1.01
    品牌
    0.97
    ُ
    0.96
    غ
    0.93
    et
    0.89
    Т
    0.88
     B
    0.86
    Act Density 0.017%

    No Known Activations