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

    Neuronpedia

    INDEX
    Explanations

    algebraic factoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ोनेशिया
    0.44
    義務
    0.42
     obligaciones
    0.40
     امنیت
    0.40
     निर्दिष्ट
    0.39
    Simulation
    0.39
    strncpy
    0.39
     มิถุนายน
    0.38
     ორგანო
    0.38
     संक्रम
    0.37
    POSITIVE LOGITS
     factorization
    1.33
     factored
    1.26
     factoring
    1.19
     factor
    1.14
     Factor
    1.11
    Factor
    1.08
     factorizar
    1.06
    factor
    1.05
     factors
    1.01
     Factors
    0.97
    Act Density 0.019%

    No Known Activations