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

    Neuronpedia

    INDEX
    Explanations

    woodchuck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     రాజు
    0.47
    ర్‌
    0.45
     कटोच
    0.45
    ÍA
    0.44
     የተቀ
    0.44
    ΙΑ
    0.43
    ల్
    0.43
    роди
    0.43
    Buch
    0.43
    ATOR
    0.43
    POSITIVE LOGITS
     Beta
    0.47
                  
    0.46
     Calculate
    0.45
    ++)
    0.45
     zahl
    0.44
     gastos
    0.43
     Allow
    0.43
     পর্যাপ্ত
    0.43
     সঠিকভাবে
    0.43
     hatta
    0.42
    Act Density 0.001%

    No Known Activations