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

    Neuronpedia

    INDEX
    Explanations

    code execution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tailored
    -0.08
     használ
    -0.07
     underserved
    -0.07
    .display
    -0.07
     لقد
    -0.07
     anos
    -0.07
    ниж
    -0.07
     recommandé
    -0.07
     direcion
    -0.07
    query
    -0.07
    POSITIVE LOGITS
    第一次
    0.10
     executes
    0.09
    执行
    0.09
     выполня
    0.09
    被
    0.09
    首次
    0.09
    Executed
    0.08
     فرصت
    0.08
     uitgevoerd
    0.08
     被
    0.08
    Act Density 0.009%

    No Known Activations