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

    Neuronpedia

    INDEX
    Explanations

    Research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    先天
    -0.08
    (val
    -0.07
    Atlantic
    -0.07
     CLOSE
    -0.07
    (Box
    -0.07
    聱
    -0.07
    .addField
    -0.07
    iad
    -0.07
     này
    -0.07
     bị
    -0.07
    POSITIVE LOGITS
    ildo
    0.08
    logo
    0.07
     specificity
    0.07
    丸
    0.07
    Prot
    0.07
     MR
    0.07
    詳細
    0.07
    反應
    0.07
    hipster
    0.06
    -data
    0.06
    Act Density 0.011%

    No Known Activations