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

    Neuronpedia

    INDEX
    Explanations

    Code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubbed
    -0.07
     rnd
    -0.07
     scept
    -0.07
     striped
    -0.07
     stabil
    -0.06
     activates
    -0.06
     Европ
    -0.06
     dataframe
    -0.06
     глиб
    -0.06
    ampp
    -0.06
    POSITIVE LOGITS
     queda
    0.08
    ']").
    0.07
    )]
    0.07
     говорить
    0.06
    )—
    0.06
     urlpatterns
    0.06
    (serializer
    0.06
     Cohen
    0.06
    Ú
    0.06
    σει
    0.06
    Act Density 0.030%

    No Known Activations