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

    Neuronpedia

    INDEX
    Explanations

    multilingual queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     および
    1.05
     ensuring
    1.02
     மற்றும்
    1.01
    および
    1.01
     प्रदान
    1.01
     вследствие
    0.99
     различных
    0.96
     establishing
    0.95
    あらゆる
    0.95
     посредством
    0.93
    POSITIVE LOGITS
     mấy
    1.60
     pakai
    1.42
     bisschen
    1.41
     punya
    1.34
     нравится
    1.31
     хочу
    1.30
     треба
    1.27
     bagus
    1.27
    买
    1.26
    เยอะ
    1.26
    Act Density 0.063%

    No Known Activations