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

    Neuronpedia

    INDEX
    Explanations

    translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Innov
    -0.10
     Delgado
    -0.09
     innovate
    -0.09
     lancement
    -0.08
    Innovation
    -0.08
     inov
    -0.08
     innovators
    -0.08
    ulsive
    -0.08
     दशक
    -0.08
    coon
    -0.08
    POSITIVE LOGITS
     traduction
    0.17
    译
    0.17
     tradução
    0.16
     translations
    0.15
     ترج
    0.15
     translation
    0.15
     tradu
    0.14
     translators
    0.14
    翻
    0.14
    _translation
    0.14
    Act Density 0.060%

    No Known Activations