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

    Neuronpedia

    INDEX
    Explanations

    special characters and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.54
    ↵
    0.50
    ro
    0.48
     earmarked
    0.44
    ander
    0.44
     Junior
    0.44
     /
    0.44
     partisans
    0.43
     blown
    0.43
     talks
    0.42
    POSITIVE LOGITS
    ند
    0.52
    ጨም
    0.49
    第一
    0.49
    iciência
    0.49
     salário
    0.48
     amarelo
    0.48
    ૯
    0.48
    મી
    0.47
    وزيع
    0.47
    ш
    0.47
    Act Density 0.003%

    No Known Activations