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

    Neuronpedia

    INDEX
    Explanations

    predicting next words for lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.61
    s
    0.46
    setzen
    0.46
    lique
    0.42
    en
    0.40
    偉
    0.39
    Pref
    0.39
    柱
    0.39
     campagna
    0.38
     campaigns
    0.38
    POSITIVE LOGITS
    úst
    0.56
    aginaw
    0.56
     Demonstrate
    0.54
     Jiang
    0.52
     创建
    0.52
     করিতেছিল
    0.52
     Became
    0.52
     अपघात
    0.51
     Bạn
    0.51
    犟
    0.51
    Act Density 0.027%

    No Known Activations