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

    Neuronpedia

    INDEX
    Explanations

    country identification and inspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.50
    <0x0D>
    0.47
    </i>
    0.46
     fille
    0.41
    \
    0.40
     商品
    0.40
     +
    0.40
     constitu
    0.40
    ᗰ
    0.40
    0.39
    POSITIVE LOGITS
    嵬
    0.48
    irrahim
    0.46
     ఏర్
    0.44
    raient
    0.44
     eagerly
    0.43
     skiers
    0.43
    蒉
    0.43
    ivasena
    0.42
    ointments
    0.42
     bowlers
    0.41
    Act Density 0.006%

    No Known Activations