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

    Neuronpedia

    INDEX
    Explanations

    freedom of assembly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डेब्यू
    0.39
     சிகிச்ச
    0.37
    ਡੇ
    0.37
    Ellis
    0.36
    扞
    0.36
     lutte
    0.35
    境界層
    0.35
     एलि
    0.34
     interleaved
    0.34
     Childs
    0.34
    POSITIVE LOGITS
     gatherings
    1.84
     gathering
    1.46
     Gather
    1.39
    聚集
    1.39
     تجمع
    1.33
     gather
    1.32
     Gathering
    1.31
    gather
    1.29
    Gather
    1.28
     gathers
    1.26
    Act Density 0.010%

    No Known Activations