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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing a personal opinion, judgement or sentiment

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     befind
    -0.56
    TagMode
    -0.50
    <bos>
    -0.49
    Джерела
    -0.44
     Majesty
    -0.44
    vosť
    -0.44
    TableHead
    -0.42
     моло
    -0.42
     '-')
    -0.42
    حياته
    -0.41
    POSITIVE LOGITS
     оригіналу
    0.77
    rungsseite
    0.69
    Sucesor
    0.66
    adpleegd
    0.64
    ijnlijk
    0.62
     وتسجيلات
    0.61
    ährend
    0.61
     abstrait
    0.60
     Forder
    0.60
    ///</
    0.59
    Act Density 12.757%

    No Known Activations