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

    Neuronpedia

    INDEX
    Explanations

    concepts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.52
    ᅢ
    0.47
    وسف
    0.46
    다
    0.46
    ين
    0.46
    のこ
    0.43
    瓄
    0.43
    잼
    0.43
    ent
    0.43
    햇
    0.43
    POSITIVE LOGITS
     ду
    0.50
     muy
    0.48
    }))$
    0.48
    }']
    0.45
     nightclubs
    0.43
     skins
    0.43
     eyewear
    0.43
     আদালতে
    0.43
     здійс
    0.43
     ০
    0.43
    Act Density 0.007%

    No Known Activations