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

    Neuronpedia

    INDEX
    Explanations

    animal training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grans
    -0.07
    ناق
    -0.07
    ời
    -0.07
    িয়ান
    -0.07
    rị
    -0.07
     abund
    -0.07
     cig
    -0.07
     resumed
    -0.07
     മാറ
    -0.07
     proteínas
    -0.07
    POSITIVE LOGITS
     प्रशिक्षण
    0.11
     تدريب
    0.11
    训练
    0.11
     tricks
    0.10
     incul
    0.10
     പരിശീല
    0.10
     trening
    0.10
    training
    0.10
    -training
    0.10
     teaches
    0.10
    Act Density 0.026%

    No Known Activations