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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     প্রদান
    -0.08
     rendre
    -0.08
    .Template
    -0.07
    Directions
    -0.07
    uniya
    -0.07
     Classe
    -0.07
    armi
    -0.07
    情况下
    -0.07
     unve
    -0.07
     عاج
    -0.07
    POSITIVE LOGITS
    以来
    0.14
     इतिहास
    0.13
     histories
    0.13
     geschiedenis
    0.12
     прошлом
    0.12
     history
    0.12
     историю
    0.12
    歴
    0.12
     прошлого
    0.12
     истории
    0.12
    Act Density 0.420%

    No Known Activations