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

    Neuronpedia

    INDEX
    Explanations

    legal clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rotational
    0.49
     graduation
    0.46
    ון
    0.46
     rotation
    0.45
     seder
    0.45
     smarter
    0.44
     interle
    0.44
     pembelian
    0.44
     Retire
    0.43
     रचना
    0.43
    POSITIVE LOGITS
    を用
    0.49
     ولي
    0.46
    を用いる
    0.45
    ”
    0.42
     આવ્યું
    0.41
    珼
    0.40
    babel
    0.40
     Ag
    0.40
    ”-
    0.40
     保
    0.39
    Act Density 0.004%

    No Known Activations