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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scientists
    -0.06
    ellig
    -0.06
    "When
    -0.06
    .Dispatcher
    -0.06
     민
    -0.06
     창
    -0.06
     erfolgreich
    -0.06
     الكتاب
    -0.06
    μένοι
    -0.06
     وابسته
    -0.06
    POSITIVE LOGITS
     strawberry
    0.07
     strawberries
    0.07
    urning
    0.07
    export
    0.07
    630
    0.06
    .shutdown
    0.06
     Walsh
    0.06
     IGNORE
    0.06
    interface
    0.06
    Techn
    0.06
    Act Density 0.001%

    No Known Activations