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

    Neuronpedia

    INDEX
    Explanations

    names, abbreviations, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ごめんなさい
    -2.64
    色んな
    -2.64
    و
    -2.59
    ↵
    -2.52
    ほんとに
    -2.47
    ほんと
    -2.44
     beberapa
    -2.39
    ꔛ
    -2.34
    阄
    -2.34
     冷凍
    -2.33
    POSITIVE LOGITS
    or
    2.69
    ！！！”
    2.59
    ,
    2.56
    ！”
    2.33
    ！！”
    2.23
     This
    2.20
    .”
    2.17
    t
    2.16
     и
    1.99
    ড
    1.99
    Act Density 0.005%

    No Known Activations