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

    Neuronpedia

    INDEX
    Explanations

    negative consequences or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మాత్రం
    0.37
    かもしれませんが
    0.35
     ఇలా
    0.31
     Gefühl
    0.30
    ？）
    0.30
     wäre
    0.29
    なども
    0.29
    等的
    0.29
    などに
    0.29
     みたい
    0.29
    POSITIVE LOGITS
     क्योंकि
    0.51
    。
    0.50
    .
    0.47
    。《
    0.44
     특히
    0.44
     terutama
    0.43
    。『
    0.42
    especially
    0.42
    <unused2200>
    0.42
    。「
    0.41
    Act Density 4.050%

    No Known Activations