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

    Neuronpedia

    INDEX
    Explanations

    Product features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Christus
    -0.09
    TG
    -0.08
     interv
    -0.08
     resin
    -0.08
     encounters
    -0.08
    形
    -0.07
     contacted
    -0.07
    ょう
    -0.07
    执
    -0.07
     alak
    -0.07
    POSITIVE LOGITS
     fonctionnalités
    0.15
     features
    0.14
     Features
    0.12
    功能
    0.12
    Features
    0.12
     امکانات
    0.12
     functionalities
    0.12
     funcionalidades
    0.12
     기능
    0.12
    _features
    0.11
    Act Density 0.082%

    No Known Activations