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

    Neuronpedia

    INDEX
    Explanations

    currency and large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -enh
    -0.07
     Rescue
    -0.07
     soph
    -0.07
    Removed
    -0.07
     lacking
    -0.07
    持有
    -0.07
    食品
    -0.07
     lh
    -0.06
     Cro
    -0.06
    保护
    -0.06
    POSITIVE LOGITS
    哪儿
    0.07
    췬
    0.07
    ."\
    0.07
    ✈
    0.07
    blr
    0.07
     zobowią
    0.07
    (!
    0.07
    やって
    0.07
    Ṡ
    0.07
    dır
    0.06
    Act Density 0.083%

    No Known Activations