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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conspiracy/organizations, mental conditions and storytelling terms

    oai_token-act-pair · gemini-2.0-flash

    State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.64
     Vrbo
    -0.45
    '/',
    -0.44
     vielmehr
    -0.44
      (
    -0.43
    versa
    -0.42
    ViewImports
    -0.41
    <bos>
    -0.41
     Schicht
    -0.41
    бираем
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.75
    IntoConstraints
    0.64
     Мексичка
    0.61
    alyptus
    0.59
    Sucesor
    0.59
    DeleteBehavior
    0.58
     Meksiku
    0.53
     Vikipedi
    0.52
     THOUGH
    0.52
    [:-
    0.52
    Act Density 1.623%

    No Known Activations