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

    Neuronpedia

    INDEX
    Explanations

    words related to thinking, opinions, and making statements

    oai_token-act-pair · gemini-2.0-flash

    Opinions and thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LEX
    -0.51
    ChildIndex
    -0.50
    UserScript
    -0.49
     Pix
    -0.48
    ưu
    -0.48
    зумі
    -0.47
    gite
    -0.46
    actionMode
    -0.46
     Ludo
    -0.45
     Lex
    -0.45
    POSITIVE LOGITS
    <bos>
    1.40
    RegistryLite
    0.58
     विश्वसनीयता
    0.55
    !*\
    0.54
    ///</
    0.54
     estimés
    0.52
    Šaltiniai
    0.52
    basicConfig
    0.52
    Бележки
    0.51
    లాలు
    0.51
    Act Density 1.165%

    No Known Activations