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

    Neuronpedia

    INDEX
    Explanations

    cities and summer clothes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    も
    0.50
     cataly
    0.48
    도
    0.47
    то
    0.47
    是最
    0.46
    ও
    0.46
    са
    0.46
     หรือ
    0.46
    ца
    0.45
     સર્
    0.45
    POSITIVE LOGITS
     शहरों
    0.49
     infringing
    0.49
     cidades
    0.46
    日本では
    0.45
     countries
    0.44
     neighbouring
    0.43
    多い
    0.41
     neighboring
    0.41
    unistd
    0.41
     harassing
    0.41
    Act Density 0.000%

    No Known Activations