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

    Neuronpedia

    INDEX
    Explanations

    website content snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ger
    -0.07
     desirable
    -0.07
    _metrics
    -0.06
     필요한
    -0.06
    如何
    -0.06
    248
    -0.06
     redeem
    -0.06
     ус
    -0.06
     kỳ
    -0.06
     meddling
    -0.06
    POSITIVE LOGITS
     indentation
    0.06
    ubuntu
    0.06
    reich
    0.06
    :normal
    0.06
    '])){
↵
    0.06
    –↵↵
    0.06
    工業
    0.06
    умов
    0.06
    áč
    0.06
     cannons
    0.06
    Act Density 0.199%

    No Known Activations