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

    Neuronpedia

    INDEX
    Explanations

    drift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -query
    -0.07
    ）
    -0.07
     agendas
    -0.06
    comment
    -0.06
    -final
    -0.06
    .neighbors
    -0.06
     víc
    -0.06
    emez
    -0.06
     può
    -0.06
     primaries
    -0.06
    POSITIVE LOGITS
     drift
    0.25
    ift
    0.14
     drifting
    0.12
     drifted
    0.11
    rift
    0.11
     thrift
    0.10
     rift
    0.09
     Rift
    0.09
    IFT
    0.09
     uplift
    0.07
    Act Density 0.002%

    No Known Activations