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

    Neuronpedia

    INDEX
    Explanations

    Legal arguments and court context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拟
    -0.07
     Masks
    -0.07
     목
    -0.06
    频
    -0.06
     Nullable
    -0.06
    _sess
    -0.06
    movie
    -0.06
     rahatsız
    -0.06
    婆
    -0.06
     mask
    -0.06
    POSITIVE LOGITS
    bulk
    0.07
     vaccinations
    0.07
     postpon
    0.07
     llev
    0.07
     uch
    0.06
     blond
    0.06
     à
    0.06
     stretched
    0.06
    ellidos
    0.06
     ░
    0.06
    Act Density 0.040%

    No Known Activations