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

    Neuronpedia

    INDEX
    Explanations

    black + word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     крас
    0.44
    捃
    0.41
     Bhojpuri
    0.39
    芑
    0.39
    areti
    0.39
    𝓲
    0.39
     đỏ
    0.39
    ন
    0.39
    𝒊
    0.39
    anju
    0.38
    POSITIVE LOGITS
     Black
    1.28
     black
    1.26
    Black
    1.19
    黑
    1.16
    black
    1.14
     黒
    1.14
     BLACK
    1.13
     কালো
    1.11
     블랙
    1.09
     黑
    1.09
    Act Density 0.019%

    No Known Activations