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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veces
    -0.07
    eníze
    -0.07
     watched
    -0.07
    ueling
    -0.07
     dazu
    -0.06
    (/^\
    -0.06
    .addSubview
    -0.06
    Prediction
    -0.06
     تحلیل
    -0.06
    -article
    -0.06
    POSITIVE LOGITS
    ”↵
    0.06
    中华
    0.06
     Seb
    0.06
    fill
    0.06
    �
    0.06
    чен
    0.06
     cannabis
    0.06
    bart
    0.06
    	work
    0.06
    πε
    0.06
    Act Density 0.022%

    No Known Activations