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

    Neuronpedia

    INDEX
    Explanations

    multilingual programming and scientific texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コラボ
    0.39
     menu
    0.36
     Crew
    0.36
    °
    0.36
    0.36
     porn
    0.35
    民族
    0.35
    画像
    0.35
     база
    0.35
    ฐ
    0.34
    POSITIVE LOGITS
    的和
    0.44
     paralelas
    0.40
     hải
    0.39
    mass
    0.39
     thời
    0.37
    kang
    0.37
     avulla
    0.37
     जल्
    0.37
    pois
    0.36
    🖒
    0.36
    Act Density 0.000%

    No Known Activations