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

    Neuronpedia

    INDEX
    Explanations

    formatting, unstructured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpre
    -0.07
    .Ship
    -0.06
    Utility
    -0.06
    컬
    -0.06
     đáp
    -0.06
     DEFIN
    -0.06
    bern
    -0.06
     Scoped
    -0.06
    Concept
    -0.06
     Realty
    -0.06
    POSITIVE LOGITS
     isKindOfClass
    0.07
    Stock
    0.06
    information
    0.06
     paintings
    0.06
     seeds
    0.06
     initiating
    0.06
     physics
    0.06
     avant
    0.06
     knots
    0.06
     room
    0.06
    Act Density 0.000%

    No Known Activations