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

    Neuronpedia

    INDEX
    Explanations

    Code/file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -around
    -0.07
     Quad
    -0.07
    ederation
    -0.06
     жит
    -0.06
    _By
    -0.06
     aluminium
    -0.06
     Karma
    -0.06
    -load
    -0.06
     Kant
    -0.06
     Coral
    -0.06
    POSITIVE LOGITS
     introduced
    0.07
    cg
    0.07
    ty
    0.06
    }\
    0.06
    ........
    0.06
    �
    0.06
     همیشه
    0.06
     Publish
    0.06
    Customer
    0.05
    Supply
    0.05
    Act Density 0.034%

    No Known Activations