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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Region
    -0.06
     Unsigned
    -0.06
    那里
    -0.06
    outs
    -0.06
    ears
    -0.06
    ancel
    -0.06
    ông
    -0.05
    eşit
    -0.05
    ,port
    -0.05
     Tell
    -0.05
    POSITIVE LOGITS
    (TreeNode
    0.07
    .Helper
    0.07
    根
    0.06
    ":"","
    0.06
     Indianapolis
    0.06
     herbal
    0.06
    HomePage
    0.06
    ${
    0.06
    џџџџџџџџ
    0.06
     مد
    0.06
    Act Density 0.003%

    No Known Activations