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

    Neuronpedia

    INDEX
    Explanations

    Question and answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стати
    -0.08
     bathrooms
    -0.07
     Texans
    -0.07
    <String
    -0.07
    альну
    -0.07
     Tài
    -0.07
     غربی
    -0.06
     정도
    -0.06
     yazılı
    -0.06
    -based
    -0.06
    POSITIVE LOGITS
    ood
    0.08
     mock
    0.07
    (empty
    0.07
     Mock
    0.07
     invited
    0.06
     Spec
    0.06
     struggling
    0.06
     Plot
    0.06
    ufe
    0.06
    icators
    0.06
    Act Density 0.048%

    No Known Activations