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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mysterious
    -0.06
    Transparent
    -0.06
     conducive
    -0.06
    萨
    -0.06
     seldom
    -0.06
    STREAM
    -0.06
    انية
    -0.06
    Salvar
    -0.06
    nav
    -0.06
    .management
    -0.06
    POSITIVE LOGITS
    .articles
    0.07
    "){
    0.07
     Franken
    0.06
    (product
    0.06
     فقط
    0.06
    .']
    0.06
     tcb
    0.06
    .mouse
    0.06
    .todos
    0.06
     tid
    0.06
    Act Density 0.049%

    No Known Activations