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

    Neuronpedia

    INDEX
    Explanations

    code/uncommon text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abe
    -0.08
     gradually
    -0.06
    FI
    -0.06
     CCTV
    -0.06
    js
    -0.06
    ο
    -0.06
    #elif
    -0.06
     BH
    -0.06
    disable
    -0.06
     med
    -0.06
    POSITIVE LOGITS
     степ
    0.06
     nepří
    0.06
    -cart
    0.06
    .isValid
    0.06
     البر
    0.06
    صة
    0.06
     домаш
    0.06
    ặc
    0.06
     giành
    0.06
     рань
    0.06
    Act Density 0.141%

    No Known Activations