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

    Neuronpedia

    INDEX
    Explanations

    code and data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enguins
    -0.07
     Nigel
    -0.06
     marty
    -0.06
     оттен
    -0.06
     Seth
    -0.06
    潜
    -0.06
    collectionView
    -0.06
    ौट
    -0.06
     isc
    -0.06
    SZ
    -0.06
    POSITIVE LOGITS
    -FIRST
    0.08
    (expression
    0.07
    (credentials
    0.07
     disparity
    0.07
    _parsed
    0.07
     verwenden
    0.06
     serialize
    0.06
     checkbox
    0.06
    argon
    0.06
    ©©
    0.06
    Act Density 0.017%

    No Known Activations