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

    Neuronpedia

    INDEX
    Explanations

    Grammatical List Elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transitional
    -0.10
     Caj
    -0.09
     succumb
    -0.09
     deadly
    -0.09
    MSG
    -0.09
     Pey
    -0.09
     نبات
    -0.09
    .Throws
    -0.08
     الرسول
    -0.08
     erupted
    -0.08
    POSITIVE LOGITS
     capabilities
    0.14
     ability
    0.14
     capability
    0.14
     fonctionnalités
    0.13
     기능
    0.13
     সক্ষম
    0.13
     Ability
    0.13
     funcionalidades
    0.13
     functionality
    0.12
    功能
    0.12
    Act Density 0.222%

    No Known Activations