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

    Neuronpedia

    INDEX
    Explanations

    focus keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.31
     (!)
    0.31
     LI
    0.30
     Durham
    0.30
    ^(
    0.30
    itul
    0.29
     Nationals
    0.29
    0.28
    ↓
    0.28
    ^)
    0.28
    POSITIVE LOGITS
     जिसमें
    0.42
     opět
    0.41
     ponownie
    0.40
     لگائیں
    0.39
     erneut
    0.38
     twofold
    0.37
     trycatch
    0.36
     जिसमे
    0.36
     inclui
    0.35
     Again
    0.34
    Act Density 0.033%

    No Known Activations