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

    Neuronpedia

    INDEX
    Explanations

    AWS Activate, reserve banking, shifted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writes
    0.93
     writer
    0.92
    Tag
    0.91
    Which
    0.91
     dise
    0.90
    writer
    0.89
    D
    0.88
    Shr
    0.88
     Tag
    0.87
     D
    0.86
    POSITIVE LOGITS
    xff
    1.22
    ammelt
    1.19
     cognac
    1.18
    空間
    1.18
    ELLOW
    1.17
     пусто
    1.16
    acaks
    1.16
     flamenco
    1.16
    nsp
    1.15
    usstsein
    1.15
    Act Density 0.000%

    No Known Activations