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

    Neuronpedia

    INDEX
    Explanations

    uv coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     constraining
    0.50
     IntelliJ
    0.47
    桟
    0.46
     дизайне
    0.46
     Repeating
    0.46
     北京
    0.46
    用餐
    0.45
     binoculars
    0.45
     गतिशील
    0.45
     OnePlus
    0.45
    POSITIVE LOGITS
    pine
    0.35
    elle
    0.34
    estone
    0.33
    ally
    0.33
    peut
    0.32
    ystone
    0.32
    従
    0.31
    esu
    0.31
    cher
    0.30
    mj
    0.30
    Act Density 0.001%

    No Known Activations