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

    Neuronpedia

    INDEX
    Explanations

    php code startup and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ($
    0.73
     $
    0.73
    Fetch
    0.70
     Ishikawa
    0.70
    瓦
    0.70
    =$
    0.69
     അവ
    0.69
    imported
    0.67
     FOREIGN
    0.67
     Import
    0.67
    POSITIVE LOGITS
    namespace
    1.01
     namespace
    0.98
    require
    0.92
     define
    0.91
    /**
    0.90
     require
    0.89
    use
    0.81
     namespaces
    0.77
    abstract
    0.77
    defined
    0.77
    Act Density 0.024%

    No Known Activations