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

    Neuronpedia

    INDEX
    Explanations

    office

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通行证
    -0.08
    (struct
    -0.07
    unsigned
    -0.07
     getchar
    -0.07
    فجر
    -0.07
    екс
    -0.07
    فاد
    -0.07
    付费
    -0.07
     Rue
    -0.07
     légère
    -0.07
    POSITIVE LOGITS
    (Chat
    0.08
    ımı
    0.08
    anguages
    0.07
    alen
    0.07
     Reduction
    0.07
    _catalog
    0.07
     completion
    0.07
     Rockets
    0.07
    TextField
    0.07
    _WIDGET
    0.07
    Act Density 0.003%

    No Known Activations