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

    Neuronpedia

    INDEX
    Explanations

    grammar and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SUBJECT
    -0.07
     dick
    -0.07
    Vehicle
    -0.07
     underground
    -0.06
    .Action
    -0.06
    .between
    -0.06
     zu
    -0.06
     produk
    -0.06
     Document
    -0.06
    .products
    -0.06
    POSITIVE LOGITS
    .delay
    0.07
    PMC
    0.07
    lassen
    0.06
     Sen
    0.06
    nými
    0.06
     Mattis
    0.06
    ?>"><
    0.06
    -Agent
    0.06
    сии
    0.06
     řešení
    0.06
    Act Density 0.040%

    No Known Activations