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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relaxation
    -0.07
     rival
    -0.07
    бира
    -0.07
    (blog
    -0.06
     syntax
    -0.06
     inventory
    -0.06
     responseBody
    -0.06
    ا
    -0.06
    _URI
    -0.06
    وی
    -0.06
    POSITIVE LOGITS
        	↵
    0.06
     Xml
    0.06
    .vec
    0.06
    ))));↵
    0.06
    :number
    0.06
     nay
    0.06
    _receipt
    0.06
    }});↵
    0.05
    ;;↵↵
    0.05
     đạo
    0.05
    Act Density 0.023%

    No Known Activations