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

    Neuronpedia

    INDEX
    Explanations

    words that are conjunctions, prepositions or relate to physical actions of looking and touching

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.57
    matchCondition
    -0.54
     فريبيس
    -0.51
     Wikispecies
    -0.51
    chelles
    -0.49
    Inflater
    -0.49
    StoryboardSegue
    -0.48
    忑
    -0.48
    مقد
    -0.48
    TypedDataSet
    -0.47
    POSITIVE LOGITS
    <bos>
    0.64
    ί
    0.61
    BeginContext
    0.60
     gra
    0.53
    şehir
    0.53
    مصادر
    0.52
    igra
    0.50
     tomorrow
    0.49
    avr
    0.49
     SqlCommand
    0.48
    Act Density 1.967%

    No Known Activations