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

    Neuronpedia

    INDEX
    Explanations

    physical substances and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lığ
    0.89
     небольшой
    0.89
    ları
    0.86
    lama
    0.83
     dumpster
    0.80
     stripes
    0.80
     edible
    0.80
     meandering
    0.80
     distressed
    0.79
    いただける
    0.79
    POSITIVE LOGITS
    anju
    0.91
    و
    0.91
    可以将
    0.89
    ν
    0.86
    とっても
    0.85
    Bat
    0.84
    源
    0.82
     thơ
    0.82
    あり
    0.81
     rö
    0.80
    Act Density 0.001%

    No Known Activations