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

    Neuronpedia

    INDEX
    Explanations

    the/one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'post
    -0.09
    пу
    -0.08
     engineering
    -0.08
     Engineering
    -0.08
     Across
    -0.08
    $post
    -0.08
     engineered
    -0.08
    .yy
    -0.08
     engineer
    -0.07
     JFile
    -0.07
    POSITIVE LOGITS
     worship
    0.11
     religions
    0.09
     fondament
    0.09
     fundament
    0.09
     relig
    0.09
     Worship
    0.09
     theology
    0.09
     divine
    0.08
     foundational
    0.08
    ศจ
    0.08
    Act Density 0.013%

    No Known Activations