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

    Neuronpedia

    INDEX
    Explanations

    tall or all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    essen
    -0.08
    death
    -0.08
    perator
    -0.07
    whose
    -0.07
    ducers
    -0.07
    (_
    -0.07
    误解
    -0.07
    Support
    -0.07
    ธ
    -0.07
     refining
    -0.07
    POSITIVE LOGITS
     Lös
    0.08
    .myapplication
    0.07
    apatkan
    0.07
    っていました
    0.07
     getAll
    0.07
    工作效率
    0.07
     lắp
    0.07
    游戏装备
    0.06
    乔治
    0.06
    觏
    0.06
    Act Density 0.008%

    No Known Activations