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

    Neuronpedia

    INDEX
    Explanations

    paragraph text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pode
    -0.07
     Journey
    -0.06
    AE
    -0.06
    ociety
    -0.06
    ň
    -0.06
     svm
    -0.06
     View
    -0.06
    logue
    -0.06
    Republic
    -0.06
     Warehouse
    -0.06
    POSITIVE LOGITS
     metabol
    0.07
     окт
    0.07
    ,:,
    0.07
    .begin
    0.06
    -mails
    0.06
     clang
    0.06
    (coords
    0.06
    ctx
    0.06
    ψ
    0.06
     Bundes
    0.06
    Act Density 0.060%

    No Known Activations