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

    Neuronpedia

    INDEX
    Explanations

    margin: property in CSS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    圆
    0.44
    any
    0.41
    zyc
    0.40
     च
    0.39
     当
    0.39
     प्ले
    0.38
     telewiz
    0.38
    iny
    0.38
     .(
    0.38
    ius
    0.37
    POSITIVE LOGITS
     purged
    0.46
    鵜
    0.40
     purified
    0.38
    purge
    0.38
     subgoal
    0.36
    Th
    0.36
    ဝန်
    0.36
     tailored
    0.35
     Kad
    0.35
     elbow
    0.35
    Act Density 0.002%

    No Known Activations