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

    Neuronpedia

    INDEX
    Explanations

    quizzes and criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.41
    b
    0.40
    -
    0.40
    기와
    0.38
    g
    0.37
     takže
    0.36
     hijab
    0.36
    bots
    0.35
     toilette
    0.34
     to
    0.34
    POSITIVE LOGITS
    PLEASE
    0.50
    :[/
    0.47
    Voici
    0.46
     निम्नलिखित
    0.45
    उदाहरण
    0.45
     கூறியதாவது
    0.45
     Voici
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    коменду
    0.44
    Вот
    0.43
    Act Density 1.673%

    No Known Activations