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

    Neuronpedia

    INDEX
    Explanations

    container

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rho
    -0.07
    ekli
    -0.07
     Yeah
    -0.06
     Geological
    -0.06
     owes
    -0.06
     pathology
    -0.06
    .emplace
    -0.06
     Sparse
    -0.06
     spanking
    -0.06
    284
    -0.06
    POSITIVE LOGITS
     container
    0.09
    container
    0.08
    (container
    0.08
    uest
    0.08
    ΑΝ
    0.08
    .container
    0.08
    pillar
    0.08
    apons
    0.07
    탄
    0.07
    Container
    0.07
    Act Density 0.011%

    No Known Activations