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

    Neuronpedia

    INDEX
    Explanations

    soft + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    侩
    0.42
    แส
    0.41
     جبر
    0.40
    笏
    0.39
    长安
    0.39
     সম্ভব
    0.38
     możli
    0.38
     बल्कि
    0.37
    ོང་
    0.37
     ممکن
    0.36
    POSITIVE LOGITS
     soft
    1.27
     Soft
    1.16
    Soft
    1.13
     softer
    1.12
    soft
    1.10
    软
    1.09
    軟
    1.01
     SOFT
    1.00
     softness
    0.95
    硬
    0.90
    Act Density 0.016%

    No Known Activations