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

    Neuronpedia

    INDEX
    Explanations

    html document start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Academia
    2.16
     таки
    1.92
     vicinity
    1.71
    ようになった
    1.67
     Bored
    1.64
     NGC
    1.64
     FTSE
    1.63
     eds
    1.61
    ခြေ
    1.56
     Assault
    1.56
    POSITIVE LOGITS
    𝐍
    2.51
    n
    2.15
    க்
    2.10
    𝐀
    2.08
    ек
    1.96
    𝐓
    1.95
    م
    1.88
    ことです
    1.88
    𝐔
    1.86
    raient
    1.86
    Act Density 0.002%

    No Known Activations