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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     full
    -0.07
    anto
    -0.07
     Wich
    -0.06
    说
    -0.06
    ьми
    -0.06
     facing
    -0.06
     Rita
    -0.06
     Isabel
    -0.06
     dư
    -0.06
     urlpatterns
    -0.06
    POSITIVE LOGITS
    posal
    0.06
     Research
    0.06
    �
    0.06
    υνα
    0.06
    àng
    0.06
     Au
    0.06
    IBUTE
    0.06
     smoking
    0.06
    vincial
    0.06
    (scale
    0.06
    Act Density 0.023%

    No Known Activations