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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ans
    -0.07
     wiring
    -0.07
     lett
    -0.07
     Battery
    -0.06
    -area
    -0.06
     Typical
    -0.06
    (location
    -0.06
     far
    -0.06
    ‍
    -0.06
    Empresa
    -0.06
    POSITIVE LOGITS
     губер
    0.07
    ISHED
    0.06
    roller
    0.06
    roe
    0.06
     publication
    0.06
     Volkswagen
    0.06
    nom
    0.06
     EventArgs
    0.06
    рун
    0.06
    ucker
    0.06
    Act Density 0.001%

    No Known Activations