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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    แสดง
    -0.07
    顯
    -0.07
    ulner
    -0.07
    ृत
    -0.06
     sod
    -0.06
    witter
    -0.06
     �
    -0.06
     saúde
    -0.06
    Invariant
    -0.06
    POSITIVE LOGITS
     basil
    0.06
     Yahoo
    0.06
    (items
    0.06
     hearts
    0.06
    ipzig
    0.05
    итися
    0.05
    KNOWN
    0.05
    (rows
    0.05
    Yahoo
    0.05
     toString
    0.05
    Act Density 0.002%

    No Known Activations