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

    Neuronpedia

    INDEX
    Explanations

    standards and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모습
    1.02
     হেসে
    0.99
     moitié
    0.97
     metade
    0.96
     charm
    0.96
     наш
    0.95
     rumores
    0.95
     encant
    0.95
     antics
    0.95
     glimpse
    0.95
    POSITIVE LOGITS
     dotycz
    1.46
     Guidelines
    1.39
    🔖
    1.35
     Methodology
    1.34
     dotyczą
    1.34
     guidelines
    1.33
     적용
    1.32
     privind
    1.31
     Recommendations
    1.29
     предусматри
    1.29
    Act Density 0.224%

    No Known Activations