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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bradford
    -0.07
     Toplam
    -0.07
    ItemCount
    -0.07
    ahat
    -0.07
    .tabs
    -0.07
     lấy
    -0.06
     penetrating
    -0.06
    arty
    -0.06
     spole
    -0.06
     XP
    -0.06
    POSITIVE LOGITS
    ละ
    0.06
    ิธ
    0.06
    这一
    0.06
     Hassan
    0.06
    ー�
    0.06
    技术
    0.06
     đường
    0.06
     해당
    0.06
     acceler
    0.05
     bishops
    0.05
    Act Density 0.082%

    No Known Activations