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

    Neuronpedia

    INDEX
    Explanations

    adoption and interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $\,.
    0.44
    闗
    0.41
     subsections
    0.40
    տր
    0.39
     itr
    0.39
     பாது
    0.39
     regione
    0.38
     ፡፡
    0.38
     región
    0.38
    コマンド
    0.38
    POSITIVE LOGITS
     artık
    0.44
    non
    0.42
     non
    0.42
     गैर
    0.42
    nga
    0.40
     freelance
    0.39
    ノン
    0.37
    Non
    0.37
    गैर
    0.37
    Airbnb
    0.37
    Act Density 0.003%

    No Known Activations