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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENTER
    -0.08
     Tanger
    -0.08
     sauna
    -0.08
    kat
    -0.08
     mediterr
    -0.08
    errer
    -0.08
    .notify
    -0.08
     sobri
    -0.07
    .enter
    -0.07
    .document
    -0.07
    POSITIVE LOGITS
     प्रश्न
    0.09
     preguntas
    0.09
     definite
    0.09
     প্রশ্ন
    0.09
     quizzes
    0.09
     ప్రశ
    0.08
     questions
    0.08
     задания
    0.08
    題
    0.08
     उत्तर
    0.08
    Act Density 0.005%

    No Known Activations