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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cano
    -0.07
     Diagnostics
    -0.07
     today
    -0.07
     diagnostics
    -0.07
     aujourd
    -0.07
     Today
    -0.07
     favorite
    -0.07
     transporte
    -0.07
    favorite
    -0.07
    ng
    -0.07
    POSITIVE LOGITS
     наоборот
    0.09
     مساحة
    0.09
     hingegen
    0.08
    ικο
    0.08
    번째
    0.08
    则
    0.08
     creatividad
    0.08
    ερ
    0.08
     Krank
    0.08
     kreative
    0.08
    Act Density 0.002%

    No Known Activations