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
     tumors
    0.50
    0.48
    laub
    0.46
     binary
    0.46
     tubers
    0.45
     biographer
    0.45
     single
    0.45
     sins
    0.45
     mergers
    0.45
     n
    0.45
    POSITIVE LOGITS
    畐
    0.52
     Música
    0.51
    㓡
    0.51
     ദേശീയ
    0.49
    ⺠
    0.49
    0.49
    頁
    0.48
     Už
    0.48
    理由
    0.47
     nationale
    0.47
    Act Density 0.000%

    No Known Activations