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

    Neuronpedia

    INDEX
    Explanations

    basic concepts and setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     komplex
    0.49
     heifer
    0.44
     phức
    0.42
    Complex
    0.41
     först
    0.41
     ඇත
    0.40
     сложно
    0.40
    午後
    0.40
    複雜
    0.39
    🍤
    0.39
    POSITIVE LOGITS
     základ
    0.47
    基本的
    0.47
     básicas
    0.45
     basic
    0.45
     Greetings
    0.45
    基本
    0.44
    Basic
    0.44
    basic
    0.43
     Installation
    0.42
     básico
    0.42
    Act Density 0.159%

    No Known Activations