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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lọc
    -0.06
     threw
    -0.06
     koneč
    -0.06
     히
    -0.06
     Lay
    -0.06
    替
    -0.06
     Ün
    -0.06
     underlying
    -0.06
    朗
    -0.06
    ρούν
    -0.06
    POSITIVE LOGITS
    _COMPAT
    0.06
     inscription
    0.06
    _COPY
    0.06
     SIG
    0.06
     disruption
    0.06
     Ver
    0.06
     voter
    0.06
     citizenship
    0.06
     appealing
    0.06
    §
    0.06
    Act Density 0.005%

    No Known Activations