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

    Neuronpedia

    INDEX
    Explanations

    crafts, monitoring, optimization, character, defenders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    사
    0.46
    我很
    0.45
    得很
    0.44
    開
    0.44
    里
    0.43
    来
    0.42
     بخشی
    0.42
    ン
    0.41
    的部分
    0.41
    一時
    0.40
    POSITIVE LOGITS
    urine
    0.52
    %!
    0.50
     ARXIV
    0.49
     bakter
    0.49
     namani
    0.43
     Escherichia
    0.43
    0.43
     bukan
    0.42
     bakteri
    0.42
    obtain
    0.42
    Act Density 0.020%

    No Known Activations