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

    Neuronpedia

    INDEX
    Explanations

    let's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     столь
    1.02
     kita
    0.94
    如此
    0.91
     Its
    0.91
    its
    0.87
    它的
    0.86
     nostru
    0.85
    Its
    0.84
     нашего
    0.83
     kami
    0.83
    POSITIVE LOGITS
     yourself
    2.05
    yourself
    1.64
     Yourself
    1.61
     yourselves
    1.56
     jezelf
    1.32
     نفسك
    1.29
     your
    1.25
    cknow
    1.21
    issez
    1.20
     wisely
    1.05
    Act Density 0.781%

    No Known Activations