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

    Neuronpedia

    INDEX
    Explanations

    names of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marketplace
    0.37
     Specials
    0.37
     lỗ
    0.37
     tarafından
    0.37
     による
    0.37
     Restaurant
    0.36
     দ্বারা
    0.36
     Yardım
    0.36
     ของ
    0.35
     Podcast
    0.35
    POSITIVE LOGITS
    stepping
    0.46
    creto
    0.44
    webpack
    0.43
    attr
    0.43
    break
    0.43
    label
    0.42
    string
    0.42
    fn
    0.42
    berapa
    0.42
    fade
    0.41
    Act Density 0.148%

    No Known Activations