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

    Neuronpedia

    INDEX
    Explanations

    Erinner, Lung, ung

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पीसीएस
    0.45
    ancake
    0.45
    িনিয়ার
    0.43
     discriminate
    0.42
     Bobby
    0.40
    魁
    0.39
    Ϻ
    0.39
    하시오
    0.38
    bollah
    0.38
    aminar
    0.38
    POSITIVE LOGITS
    ung
    2.48
    UNG
    2.42
    Ung
    2.22
     Ung
    2.16
    Jung
    2.16
     Jung
    2.14
     ung
    2.14
    Lung
    1.94
    lung
    1.93
     lung
    1.92
    Act Density 0.021%

    No Known Activations