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

    Neuronpedia

    INDEX
    Explanations

    errors, mistakes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    府
    -0.08
     gebruikte
    -0.08
    riel
    -0.08
     terreno
    -0.08
     lại
    -0.08
    宣
    -0.08
     warr
    -0.07
     affin
    -0.07
     प्रम
    -0.07
    中文版
    -0.07
    POSITIVE LOGITS
    =train
    0.09
    =models
    0.08
     ginger
    0.08
     হিসাবে
    0.08
    });
    0.07
     mobiles
    0.07
     saying
    0.07
     کہ
    0.07
     મુજબ
    0.07
     brit
    0.07
    Act Density 0.170%

    No Known Activations