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

    Neuronpedia

    INDEX
    Explanations

    Alberti Bass, Fetch, sodium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    与其
    0.47
     কয়েক
    0.44
     ন্যায্য
    0.43
     dran
    0.42
     médias
    0.42
     commensurate
    0.41
     새벽
    0.41
     বিধান
    0.41
    érez
    0.41
    ▐
    0.41
    POSITIVE LOGITS
    /{
    0.43
    yyati
    0.42
    יו
    0.41
    مث
    0.41
    后台
    0.40
     Servi
    0.40
    brushes
    0.39
    ndi
    0.39
    plac
    0.39
    மன
    0.39
    Act Density 0.024%

    No Known Activations