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

    Neuronpedia

    INDEX
    Explanations

    data compression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sig
    -0.07
     bfs
    -0.06
    qc
    -0.06
    gı
    -0.06
     반
    -0.06
    partment
    -0.06
    awai
    -0.06
    gomery
    -0.06
     massive
    -0.06
    Russian
    -0.06
    POSITIVE LOGITS
     профессиональ
    0.07
    ["
    0.06
     DISCLAIMER
    0.06
     genel
    0.06
    rabilir
    0.06
     AppBundle
    0.06
    ："
    0.06
     enroll
    0.06
    .ค
    0.06
    )**
    0.06
    Act Density 0.029%

    No Known Activations