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

    Neuronpedia

    INDEX
    Explanations

    folding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    桓
    0.43
     harry
    0.40
     ctx
    0.39
     भीड़
    0.39
    ออนไลน์
    0.37
     Netzwerk
    0.36
     descom
    0.36
    ctx
    0.35
     statistical
    0.35
     izinsuku
    0.35
    POSITIVE LOGITS
     folding
    2.16
     folded
    2.14
     fold
    2.05
     folds
    2.00
     Folding
    1.94
    Folding
    1.90
     Fold
    1.88
    folded
    1.84
    Fold
    1.81
    折り
    1.73
    Act Density 0.034%

    No Known Activations