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

    Neuronpedia

    INDEX
    Explanations

    InputStream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Redux
    -0.07
    مواطن
    -0.07
     lear
    -0.07
    $template
    -0.06
    maf
    -0.06
     Promise
    -0.06
    refixer
    -0.06
    <Animator
    -0.06
    鸯
    -0.06
    tyard
    -0.06
    POSITIVE LOGITS
    ализ
    0.07
    city
    0.07
     Chop
    0.07
    癖
    0.07
    lichkeit
    0.07
    acity
    0.07
    .pick
    0.07
    冷藏
    0.07
    Fabric
    0.07
    Units
    0.07
    Act Density 0.001%

    No Known Activations