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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نة
    -0.08
    .kernel
    -0.08
    KERNEL
    -0.07
     Economist
    -0.07
     Final
    -0.07
    (Level
    -0.06
     nel
    -0.06
    <Entry
    -0.06
    (Test
    -0.06
     multitude
    -0.06
    POSITIVE LOGITS
    孢
    0.08
    サプリ
    0.08
    loads
    0.08
    缆
    0.07
     Didn
    0.07
    -placeholder
    0.07
    请联系
    0.06
    氧
    0.06
     intimately
    0.06
    -script
    0.06
    Act Density 0.116%

    No Known Activations