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

    Neuronpedia

    INDEX
    Explanations

    showdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tres
    0.96
    дава
    0.84
     своё
    0.82
    dream
    0.80
    aadhar
    0.79
    tiles
    0.79
     vadati
    0.78
    two
    0.77
    tu
    0.77
     откры
    0.77
    POSITIVE LOGITS
     Warehouse
    0.79
     largely
    0.75
     people
    0.75
     Artinya
    0.74
     can
    0.74
     warehouse
    0.73
     purifier
    0.73
    ディション
    0.73
     certificates
    0.72
     retailers
    0.72
    Act Density 0.001%

    No Known Activations