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

    Neuronpedia

    INDEX
    Explanations

    nice to meet you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tekanan
    0.48
    Primitive
    0.46
     tumeur
    0.41
     сило
    0.41
     tinh
    0.40
     presión
    0.40
    基本的
    0.40
     değ
    0.39
    鍼
    0.39
    SUS
    0.39
    POSITIVE LOGITS
    ortes
    0.46
     Software
    0.42
    listings
    0.42
    isol
    0.41
    轎
    0.41
     software
    0.41
    踴
    0.40
     गवर्न
    0.38
     TLC
    0.38
    शासित
    0.38
    Act Density 0.000%

    No Known Activations