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
     officiers
    -0.64
     Canadian
    -0.59
     Canada
    -0.58
     Canadá
    -0.57
     côtes
    -0.53
     maș
    -0.53
     détru
    -0.52
     state
    -0.52
     State
    -0.49
     dignité
    -0.49
    POSITIVE LOGITS
    expandindo
    0.70
     censiti
    0.63
     OFDb
    0.61
    RegistryLite
    0.61
    SequentialGroup
    0.60
    BufferException
    0.60
    ViewInit
    0.59
    Portail
    0.57
     ioutil
    0.56
    principalTable
    0.56
    Act Density 0.037%

    No Known Activations