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

    Neuronpedia

    INDEX
    Explanations

    basic concepts and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ographically
    0.92
    OVERRIDES
    0.87
     superson
    0.85
     artisanal
    0.85
     magnesium
    0.85
     exclusivamente
    0.84
    ုတ်
    0.83
     золото
    0.83
    ologically
    0.83
     scandal
    0.83
    POSITIVE LOGITS
    基本
    0.74
     basic
    0.71
    基本的な
    0.64
    基本的
    0.64
    Introduction
    0.63
     Basic
    0.62
    的基本
    0.61
    Arrays
    0.59
    Basic
    0.58
    basic
    0.58
    Act Density 1.228%

    No Known Activations